120 Years of Olympics History: Athlete, GDP, Result

1896 - 2016

from IPython.display import Image
Image(filename = "ol_img.jpg", width=1000)

!pip install xgboost

Collecting xgboost
  Using cached xgboost-1.5.2-py3-none-win_amd64.whl (106.6 MB)
Requirement already satisfied: scipy in c:\users\shubham kumar\anaconda3\lib\site-packages (from xgboost) (1.7.1)
Requirement already satisfied: numpy in c:\users\shubham kumar\anaconda3\lib\site-packages (from xgboost) (1.20.3)
Installing collected packages: xgboost
Successfully installed xgboost-1.5.2

# Import all required libraries

import numpy as np
%matplotlib inline
import pandas as pd
import seaborn as sns
from sklearn.svm import SVC
import matplotlib.pyplot as plt
from xgboost import XGBClassifier
import sklearn.metrics as metrics
from sklearn.decomposition import PCA
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import mean_squared_error
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_absolute_error
from sklearn.tree import DecisionTreeClassifier
from sklearn.preprocessing import OneHotEncoder
#from xgboost.xgbclassifier import XGBClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import plot_confusion_matrix
from sklearn.neighbors import KNeighborsClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_auc_score, r2_score
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix, accuracy_score

# Upload Athlete dataset
dfa = pd.read_csv('athlete_events.csv')
dfa

	ID	Name	Sex	Age	Height	Weight	Team	NOC	Games	Year	Season	City	Sport	Event	Medal
0	1	A Dijiang	M	24.0	180.0	80.0	China	CHN	1992 Summer	1992	Summer	Barcelona	Basketball	Basketball Men's Basketball	NaN
1	2	A Lamusi	M	23.0	170.0	60.0	China	CHN	2012 Summer	2012	Summer	London	Judo	Judo Men's Extra-Lightweight	NaN
2	3	Gunnar Nielsen Aaby	M	24.0	NaN	NaN	Denmark	DEN	1920 Summer	1920	Summer	Antwerpen	Football	Football Men's Football	NaN
3	4	Edgar Lindenau Aabye	M	34.0	NaN	NaN	Denmark/Sweden	DEN	1900 Summer	1900	Summer	Paris	Tug-Of-War	Tug-Of-War Men's Tug-Of-War	Gold
4	5	Christine Jacoba Aaftink	F	21.0	185.0	82.0	Netherlands	NED	1988 Winter	1988	Winter	Calgary	Speed Skating	Speed Skating Women's 500 metres	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
271111	135569	Andrzej ya	M	29.0	179.0	89.0	Poland-1	POL	1976 Winter	1976	Winter	Innsbruck	Luge	Luge Mixed (Men)'s Doubles	NaN
271112	135570	Piotr ya	M	27.0	176.0	59.0	Poland	POL	2014 Winter	2014	Winter	Sochi	Ski Jumping	Ski Jumping Men's Large Hill, Individual	NaN
271113	135570	Piotr ya	M	27.0	176.0	59.0	Poland	POL	2014 Winter	2014	Winter	Sochi	Ski Jumping	Ski Jumping Men's Large Hill, Team	NaN
271114	135571	Tomasz Ireneusz ya	M	30.0	185.0	96.0	Poland	POL	1998 Winter	1998	Winter	Nagano	Bobsleigh	Bobsleigh Men's Four	NaN
271115	135571	Tomasz Ireneusz ya	M	34.0	185.0	96.0	Poland	POL	2002 Winter	2002	Winter	Salt Lake City	Bobsleigh	Bobsleigh Men's Four	NaN

271116 rows × 15 columns

Content

• The file athlete_events.csv contains 271116 rows and 15 columns. Each row corresponds to an individual athlete competing in an individual Olympic event (athlete-events). The columns are:

• ID - Unique number for each athlete

• Name - Athlete's name
• Sex - Male(M) or Female(F)
• Age - Integer
• Height - In centimeters
• Weight - In kilograms
• Team - Team name
• NOC - National Olympic Committee 3-letter code
• Games - Year and season
• Year - Integer
• Season - Summer or Winter
• City - Host city
• Sport - Sport
• Event - Event
• Medal - Gold, Silver, Bronze, or NA

dfa.shape # Shape of Athlete dataset(Rows, Columns)

(271116, 15)

# Upload Region Dataset

dfr = pd.read_csv('noc_regions.csv')
dfr.drop('notes', axis=1, inplace=True)
dfr.head(5)

	NOC	region
0	AFG	Afghanistan
1	AHO	Curacao
2	ALB	Albania
3	ALG	Algeria
4	AND	Andorra

# Merge Region into Athlete Dataset

df = dfa.merge(dfr, how='left',on='NOC')
df

	ID	Name	Sex	Age	Height	Weight	Team	NOC	Games	Year	Season	City	Sport	Event	Medal	region
0	1	A Dijiang	M	24.0	180.0	80.0	China	CHN	1992 Summer	1992	Summer	Barcelona	Basketball	Basketball Men's Basketball	NaN	China
1	2	A Lamusi	M	23.0	170.0	60.0	China	CHN	2012 Summer	2012	Summer	London	Judo	Judo Men's Extra-Lightweight	NaN	China
2	3	Gunnar Nielsen Aaby	M	24.0	NaN	NaN	Denmark	DEN	1920 Summer	1920	Summer	Antwerpen	Football	Football Men's Football	NaN	Denmark
3	4	Edgar Lindenau Aabye	M	34.0	NaN	NaN	Denmark/Sweden	DEN	1900 Summer	1900	Summer	Paris	Tug-Of-War	Tug-Of-War Men's Tug-Of-War	Gold	Denmark
4	5	Christine Jacoba Aaftink	F	21.0	185.0	82.0	Netherlands	NED	1988 Winter	1988	Winter	Calgary	Speed Skating	Speed Skating Women's 500 metres	NaN	Netherlands
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
271111	135569	Andrzej ya	M	29.0	179.0	89.0	Poland-1	POL	1976 Winter	1976	Winter	Innsbruck	Luge	Luge Mixed (Men)'s Doubles	NaN	Poland
271112	135570	Piotr ya	M	27.0	176.0	59.0	Poland	POL	2014 Winter	2014	Winter	Sochi	Ski Jumping	Ski Jumping Men's Large Hill, Individual	NaN	Poland
271113	135570	Piotr ya	M	27.0	176.0	59.0	Poland	POL	2014 Winter	2014	Winter	Sochi	Ski Jumping	Ski Jumping Men's Large Hill, Team	NaN	Poland
271114	135571	Tomasz Ireneusz ya	M	30.0	185.0	96.0	Poland	POL	1998 Winter	1998	Winter	Nagano	Bobsleigh	Bobsleigh Men's Four	NaN	Poland
271115	135571	Tomasz Ireneusz ya	M	34.0	185.0	96.0	Poland	POL	2002 Winter	2002	Winter	Salt Lake City	Bobsleigh	Bobsleigh Men's Four	NaN	Poland

271116 rows × 16 columns

# Drop Unessential Columns
df.drop(['ID', 'Team', 'Games'], axis=1, inplace=True)
df

	Name	Sex	Age	Height	Weight	NOC	Year	Season	City	Sport	Event	Medal	region
0	A Dijiang	M	24.0	180.0	80.0	CHN	1992	Summer	Barcelona	Basketball	Basketball Men's Basketball	NaN	China
1	A Lamusi	M	23.0	170.0	60.0	CHN	2012	Summer	London	Judo	Judo Men's Extra-Lightweight	NaN	China
2	Gunnar Nielsen Aaby	M	24.0	NaN	NaN	DEN	1920	Summer	Antwerpen	Football	Football Men's Football	NaN	Denmark
3	Edgar Lindenau Aabye	M	34.0	NaN	NaN	DEN	1900	Summer	Paris	Tug-Of-War	Tug-Of-War Men's Tug-Of-War	Gold	Denmark
4	Christine Jacoba Aaftink	F	21.0	185.0	82.0	NED	1988	Winter	Calgary	Speed Skating	Speed Skating Women's 500 metres	NaN	Netherlands
...	...	...	...	...	...	...	...	...	...	...	...	...	...
271111	Andrzej ya	M	29.0	179.0	89.0	POL	1976	Winter	Innsbruck	Luge	Luge Mixed (Men)'s Doubles	NaN	Poland
271112	Piotr ya	M	27.0	176.0	59.0	POL	2014	Winter	Sochi	Ski Jumping	Ski Jumping Men's Large Hill, Individual	NaN	Poland
271113	Piotr ya	M	27.0	176.0	59.0	POL	2014	Winter	Sochi	Ski Jumping	Ski Jumping Men's Large Hill, Team	NaN	Poland
271114	Tomasz Ireneusz ya	M	30.0	185.0	96.0	POL	1998	Winter	Nagano	Bobsleigh	Bobsleigh Men's Four	NaN	Poland
271115	Tomasz Ireneusz ya	M	34.0	185.0	96.0	POL	2002	Winter	Salt Lake City	Bobsleigh	Bobsleigh Men's Four	NaN	Poland

271116 rows × 13 columns

df.describe()

	Age	Height	Weight	Year
count	261642.000000	210945.000000	208241.000000	271116.000000
mean	25.556898	175.338970	70.702393	1978.378480
std	6.393561	10.518462	14.348020	29.877632
min	10.000000	127.000000	25.000000	1896.000000
25%	21.000000	168.000000	60.000000	1960.000000
50%	24.000000	175.000000	70.000000	1988.000000
75%	28.000000	183.000000	79.000000	2002.000000
max	97.000000	226.000000	214.000000	2016.000000

df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 271116 entries, 0 to 271115
Data columns (total 13 columns):
 #   Column  Non-Null Count   Dtype  
---  ------  --------------   -----  
 0   Name    271116 non-null  object 
 1   Sex     271116 non-null  object 
 2   Age     261642 non-null  float64
 3   Height  210945 non-null  float64
 4   Weight  208241 non-null  float64
 5   NOC     271116 non-null  object 
 6   Year    271116 non-null  int64  
 7   Season  271116 non-null  object 
 8   City    271116 non-null  object 
 9   Sport   271116 non-null  object 
 10  Event   271116 non-null  object 
 11  Medal   39783 non-null   object 
 12  region  271116 non-null  object 
dtypes: float64(3), int64(1), object(9)
memory usage: 29.0+ MB

# Save new dataset raw dataset
#df.to_csv('ath_data.csv')

print("Age of the Participants :\n\n", df.Age.sort_values(ascending=True).unique())

Age of the Participants :

 [10. 11. 12. 13. 14. 15. 16. 17. 18. 19. 20. 21. 22. 23. 24. 25. 26. 27.
 28. 29. 30. 31. 32. 33. 34. 35. 36. 37. 38. 39. 40. 41. 42. 43. 44. 45.
 46. 47. 48. 49. 50. 51. 52. 53. 54. 55. 56. 57. 58. 59. 60. 61. 62. 63.
 64. 65. 66. 67. 68. 69. 70. 71. 72. 73. 74. 75. 76. 77. 80. 81. 84. 88.
 96. 97. nan]

print("Height of the Participants : \n\n", df.Height.sort_values(ascending=True).unique())

Height of the Participants : 

 [127. 128. 130. 131. 132. 133. 135. 136. 137. 138. 139. 140. 141. 142.
 143. 144. 145. 146. 147. 148. 149. 150. 151. 152. 153. 154. 155. 156.
 157. 158. 159. 160. 161. 162. 163. 164. 165. 166. 167. 168. 169. 170.
 171. 172. 173. 174. 175. 176. 177. 178. 179. 180. 181. 182. 183. 184.
 185. 186. 187. 188. 189. 190. 191. 192. 193. 194. 195. 196. 197. 198.
 199. 200. 201. 202. 203. 204. 205. 206. 207. 208. 209. 210. 211. 212.
 213. 214. 215. 216. 217. 218. 219. 220. 221. 223. 226.  nan]

print("Weigh of the Participants: \n\n", df.Weight.sort_values(ascending=True).unique())

Weigh of the Participants: 

 [ 25.          28.          30.          31.          32.
  33.          34.          35.          36.          37.
  38.          39.          40.          41.          42.
  43.          44.          45.          46.          47.
  48.          48.5         49.          49.5         50.
  51.          51.5         52.          52.5         53.
  53.5         54.          54.5         55.          55.5
  56.          56.5         57.          57.5         58.
  58.5         59.          59.5         60.          60.5
  61.          61.5         62.          62.5         63.
  63.5         64.          64.5         65.          65.5
  66.          66.5         67.          67.5         68.
  68.5         69.          69.5         70.          70.5
  71.          71.5         72.          72.5         73.
  73.5         74.          74.5         74.66666667  75.
  75.5         76.          76.5         77.          77.33333333
  77.5         78.          78.5         79.          79.5
  80.          80.5         81.          81.5         82.
  82.5         83.          83.5         84.          84.5
  85.          85.5         86.          86.5         87.
  87.5         88.          88.5         89.          89.5
  90.          90.5         91.          91.5         92.
  92.5         93.          93.5         94.          95.
  95.5         96.          96.5         97.          97.5
  98.          98.5         99.         100.         100.5
 101.         101.5        102.         102.5        103.
 103.5        104.         104.5        105.         105.5
 106.         106.5        107.         107.5        108.
 108.5        109.         109.5        110.         111.
 112.         112.5        113.         114.         115.
 116.         116.5        117.         117.5        118.
 118.5        119.         120.         121.         121.5
 122.         122.5        123.         123.5        124.
 125.         126.         127.         127.5        128.
 129.         129.5        130.         130.5        131.
 131.5        132.         133.         133.5        134.
 135.         135.5        136.         137.         137.5
 138.         138.5        139.         140.         141.
 142.         143.         144.         145.         146.
 146.5        147.         148.         149.         150.
 151.         152.         154.         155.         156.
 158.         160.         161.         163.         165.
 167.         170.         175.         176.5        178.
 180.         182.         190.         198.         214.
          nan]

print("Olympics happend in these years :\n\n",df.Year.sort_values(ascending=True).unique())

Olympics happend in these years :

 [1896 1900 1904 1906 1908 1912 1920 1924 1928 1932 1936 1948 1952 1956
 1960 1964 1968 1972 1976 1980 1984 1988 1992 1994 1996 1998 2000 2002
 2004 2006 2008 2010 2012 2014 2016]

# Count How many null values in each columns
df.isnull().sum()

Name           0
Sex            0
Age         9474
Height     60171
Weight     62875
NOC            0
Year           0
Season         0
City           0
Sport          0
Event          0
Medal     231333
region         0
dtype: int64

# Viewing missing value with help of heatmap
plt.figure(figsize=(20,8))
sns.heatmap(df.isnull())
plt.show()

Data Cleaning

Cleanning Data

• Change name of some countries and others
• Age contains null values, Fill with mean/median.
• Height contains nulll values, Fill with mean/median.
• Weight contains null values, Fill with mean/median.
• Medal has null values, Fill with No Medal.

Naming Conversion

#df[df.region=='UK']
#df[df.region=='Trinidad']
df.region.replace({"UK":'United Kingdom', "Trinidad":'Trinidad and Tobago'},inplace=True)

df.rename(columns={'Sex':'Gender'},inplace=True)

df.rename(columns={'region':'Region'},inplace=True)

Drop Duplicates

# df.duplicated().sum()
# df.drop_duplicates(keep='last', inplace=True, ignore_index=True )

# df.shape

# Drop duplicates values on the basis of some columns.
df = df.drop_duplicates(subset=['Name', 'NOC', 'Season', 'City', 'Sport', 'Event', 'Medal'])

# We have a new shaped dataset
df.shape

(269693, 13)

df.isnull().sum()

Name           0
Gender         0
Age         9307
Height     58794
Weight     61507
NOC            0
Year           0
Season         0
City           0
Sport          0
Event          0
Medal     229928
Region         0
dtype: int64

Age

# df.Age.isnull().sum()

df['Age'].mean() #mean of Age column
df.Age.fillna(df['Age'].mean(), inplace=True) #fill with mean values and change parmanently  
df.Age.isnull().sum() # Check have there any many null values or not. 
df['Age'] = df['Age'].astype(int) # Change datatype into integer.

C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\pandas\core\generic.py:6392: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  return self._update_inplace(result)
C:\Users\SHUBHA~1\AppData\Local\Temp/ipykernel_11732/1063820441.py:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['Age'] = df['Age'].astype(int) # Change datatype into integer.

Height

h = df.Height.mean()
h

175.33911493179198

m = df.Height.median()
m

175.0

df.Height.fillna(h, inplace=True)

df.Height.isnull().sum()

0

df['Height'] = df['Height'].astype(int)

C:\Users\SHUBHA~1\AppData\Local\Temp/ipykernel_11732/2033992823.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['Height'] = df['Height'].astype(int)

Weight

# df.Weight.isnull().sum()

w_md = df.Weight.median()
w_md

70.0

w_mn = df.Weight.mean()
w_mn

70.70152171615766

df.Weight.mean()
df.Weight.fillna(df.Weight.mean(), inplace=True)
df['Weight'] = df['Weight'].astype(int)
df.isnull().sum()

C:\Users\SHUBHA~1\AppData\Local\Temp/ipykernel_11732/2753073615.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['Weight'] = df['Weight'].astype(int)

Name           0
Gender         0
Age            0
Height         0
Weight         0
NOC            0
Year           0
Season         0
City           0
Sport          0
Event          0
Medal     229928
Region         0
dtype: int64

display(df.dtypes)

Name      object
Gender    object
Age        int32
Height     int32
Weight     int32
NOC       object
Year       int64
Season    object
City      object
Sport     object
Event     object
Medal     object
Region    object
dtype: object

df.shape

(269693, 13)

# Save cleaned dataset(except medal) in our PC
# cl_df = df
# cl_df = cl_df.dropna()
# cl_df.isnull().sum()
# cl_df.to_csv("clnRowDt.csv")

# cl_df.shape

Visualization

1. Gender wise distribution

1. Total Participants

# Find how many male and female participants were in olympics game
# Here, I have work on raw dataset
gender = df['Gender'].value_counts()
print('Total Male(M) and Female(F) paricipants :- ')
print(gender)

Total Male(M) and Female(F) paricipants :- 
M    195318
F     74375
Name: Gender, dtype: int64

plt.figure(figsize = (16,9)) # figure size with ratio 16:9
sns.set(style='darkgrid',) # background darkgrid style of graph 
plt.show()
sns.countplot(df.Gender)
plt.title('Total Participants \n (M = Male || F = Female) \n')

<Figure size 1152x648 with 0 Axes>

C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

Text(0.5, 1.0, 'Total Participants \n (M = Male || F = Female) \n')

# Find how %age of both partcipants
plt.figure(figsize=(12,8))
plt.title('Gender Distribution')
plt.pie(gender, labels=gender.index, autopct='%1.1f%%', startangle=90, shadow=True);

2. Male and Female, Who won any medal

Female

# We found how many Gold, Silver, Bronze Medals won by women?
female = df[df.Gender == 'F']
female=female.dropna()
f = female.Medal.value_counts()
print(f)
plt.figure(figsize=(12,8))
plt.title('Won By Female Participants')
plt.pie(f, labels=f.index, autopct='%1.1f%%', startangle=90, shadow=True);

Bronze    3771
Gold      3747
Silver    3733
Name: Medal, dtype: int64

Male

# We found how many Gold, Silver, Bronze Medals won by women?

male = df[df.Gender == 'M']
male=male.dropna()
m = male.Medal.value_counts()
print(m)
plt.figure(figsize=(12,8))
plt.title('Won By Male Participants')
plt.pie(m, labels=m.index, autopct='%1.1f%%', startangle=90, shadow=True);

Gold      9621
Bronze    9521
Silver    9372
Name: Medal, dtype: int64

2. Country wise distribution

1. Top 50 participants countries

#Top 50 countries participating
t50_countries = df.Region.value_counts().sort_values(ascending=False).head(50)
t50_countries
# df.shape

USA               18603
Germany           15787
France            12539
United Kingdom    12117
Russia            11692
Italy             10668
Canada             9681
Japan              8422
Sweden             8287
Australia          7723
Hungary            6552
Czech Republic     6405
Poland             6158
Switzerland        6083
Netherlands        5781
Finland            5467
Spain              5313
China              5138
Austria            5076
Norway             4954
South Korea        4462
Romania            4400
Brazil             3848
Belgium            3780
Denmark            3531
Bulgaria           3529
Argentina          3296
Serbia             3292
Greece             3189
Mexico             2865
Ukraine            2559
Cuba               2479
New Zealand        2342
Belarus            1787
South Africa       1699
Egypt              1620
Portugal           1522
Kazakhstan         1429
India              1406
Turkey             1355
Ireland            1323
Slovenia           1111
Taiwan             1097
Colombia           1069
Slovakia           1055
Luxembourg          972
Latvia              937
Puerto Rico         927
Chile               925
Venezuela           925
Name: Region, dtype: int64

# 18603 times participant represented USA. One person play many format in his/her Sports in particular Year.

#plot for the top 50 countries

plt.figure(figsize=(30,25))
plt.xticks(rotation=90)
plt.title('Overall participation by Country')
plt.xlabel('Countries', fontsize=15)
sns.barplot(x=t50_countries, y=t50_countries.index, palette = 'rocket');

# Drop all null values and stored in a new varable called dff.

dff = df.dropna()
dff.reset_index(drop=True, inplace=True)

# dff.isnull().sum()
# dff.shape

d1 = dff[['Region', 'Medal']]
d1.head(3)

	Region	Medal
0	Denmark	Gold
1	Finland	Bronze
2	Finland	Bronze

x = d1[d1.Medal == 'Gold'].Region.value_counts().sort_values(ascending=False).head(50)
print("Top 50 countries won Gold Medal.\n",x.head())
y = d1[d1.Medal == 'Silver'].Region.value_counts().sort_values(ascending=False).head(50)
print("\nTop 50 countries won Silver Medal.\n",y.head())
z = d1[d1.Medal == 'Bronze'].Region.value_counts().sort_values(ascending=False).head(50)
print("\nTop 50 countries won Bronze Medal.\n",z.head())

Top 50 countries won Gold Medal.
 USA               2638
Russia            1599
Germany           1301
United Kingdom     677
Italy              575
Name: Region, dtype: int64

Top 50 countries won Silver Medal.
 USA               1640
Germany           1195
Russia            1170
United Kingdom     739
France             602
Name: Region, dtype: int64

Top 50 countries won Bronze Medal.
 USA               1358
Germany           1260
Russia            1178
France             666
United Kingdom     651
Name: Region, dtype: int64

# Shown how many 
plt.figure(figsize=(20,15))
plt.xticks(rotation=90)

plt.subplot(1,3,1)
plt.title('Won Gold By Top 50 Countries', fontsize=15)
#plt.xlabel('Countries', fontsize=15)
plt.ylabel('Gold Medals', fontsize=15)
sns.barplot(x=x, y=x.index, palette = 'rocket');
#sns.lineplot(x=x, y=x.index, palette = 'crest');

plt.subplot(1,3,2)
plt.title('Won Silver By Top 50 Countries', fontsize=15)
#plt.xlabel('Countries', fontsize=15)
plt.ylabel('Silver Medals', fontsize=15)
sns.barplot(x=y, y=y.index, palette = 'rocket');
#sns.lineplot(x=y, y=y.index, color='b', palette = 'crest');

plt.subplot(1,3,3)
plt.title('Won Silver By Top 50 Countries', fontsize=15)
plt.xlabel('Countries', fontsize=15)
plt.ylabel('Bronze Medals', fontsize=15)
sns.barplot(x=z, y=z.index, palette = 'rocket');
#sns.lineplot(x=z, y=z.index, color='b', palette = 'crest');

plt.tight_layout()

3. Year Wise Medal Distribution

dff.head()

	Name	Gender	Age	Height	Weight	NOC	Year	Season	City	Sport	Event	Medal	Region
0	Edgar Lindenau Aabye	M	34	175	70	DEN	1900	Summer	Paris	Tug-Of-War	Tug-Of-War Men's Tug-Of-War	Gold	Denmark
1	Arvo Ossian Aaltonen	M	30	175	70	FIN	1920	Summer	Antwerpen	Swimming	Swimming Men's 200 metres Breaststroke	Bronze	Finland
2	Arvo Ossian Aaltonen	M	30	175	70	FIN	1920	Summer	Antwerpen	Swimming	Swimming Men's 400 metres Breaststroke	Bronze	Finland
3	Juhamatti Tapio Aaltonen	M	28	184	85	FIN	2014	Winter	Sochi	Ice Hockey	Ice Hockey Men's Ice Hockey	Bronze	Finland
4	Paavo Johannes Aaltonen	M	28	175	64	FIN	1948	Summer	London	Gymnastics	Gymnastics Men's Individual All-Around	Bronze	Finland

yr = dff[['Year', 'Medal']]
yr.Medal.value_counts()

Gold      13368
Bronze    13292
Silver    13105
Name: Medal, dtype: int64

yr.Year.value_counts()

2008    2048
1992    2030
2016    2023
2000    2004
2004    2001
2012    1941
1988    1845
1996    1842
1984    1698
1980    1602
1976    1531
1972    1414
1920    1308
1968    1254
1964    1215
1960    1058
1956    1043
1952    1033
1936    1025
1948     985
1924     962
1912     941
1908     831
1928     823
1932     739
2014     597
1900     593
2006     526
2010     520
1904     486
2002     477
1906     457
1998     439
1994     331
1896     143
Name: Year, dtype: int64

# Medals won by each year
plt.figure(figsize=(20,15))
plt.xticks(rotation=90)

plt.subplot(3,1,1)
plt.title('Year wise distribution for Medals', fontsize=15)
plt.xlabel('Years', fontsize=15)
plt.ylabel('No. of Medals', fontsize=15)
sns.countplot(x=yr.Year, palette = 'Spectral');
# sns.lineplot(x=g.index, y=g, palette = 'rocket');

g = yr[yr.Medal == 'Gold'].Year.value_counts().sort_index(ascending=True).head(50)
print('Won Bronze Medal in each year: \n', g.head())
s = yr[yr.Medal == 'Silver'].Year.value_counts().sort_index(ascending=True).head(50)
print('\nWon Bronze Medal in each year: \n', s.head())
b = yr[yr.Medal == 'Bronze'].Year.value_counts().sort_index(ascending=True).head(50)
print('\nWon Bronze Medal in each year: \n',b.head(5))

Won Bronze Medal in each year: 
 1896     62
1900    198
1904    173
1906    156
1908    294
Name: Year, dtype: int64

Won Bronze Medal in each year: 
 1896     43
1900    220
1904    163
1906    156
1908    281
Name: Year, dtype: int64

Won Bronze Medal in each year: 
 1896     38
1900    175
1904    150
1906    145
1908    256
Name: Year, dtype: int64

plt.figure(figsize=(20,15))
plt.xticks(rotation=90)

plt.subplot(3,1,1)
plt.title('Year wise distribution for Gold Medals', fontsize=15)
#plt.xlabel('Countries', fontsize=15)
plt.ylabel('Gold Medals', fontsize=15)
sns.barplot(x=g.index, y=g, palette = 'Spectral');
# sns.lineplot(x=g.index, y=g, palette = 'rocket');

plt.subplot(3,1,2)
plt.title('Year wise distribution for Silver Medals', fontsize=15)
#plt.xlabel('Countries', fontsize=15)
plt.ylabel('Silver Medals', fontsize=15)
sns.barplot(x=s.index, y=s, palette = 'Spectral');

plt.subplot(3,1,3)
plt.title('Year wise distribution for Bronze Medals', fontsize=15)
plt.xlabel('Countries', fontsize=15)
plt.ylabel('Bronze Medals', fontsize=15)
sns.barplot(x=b.index, y=b, palette = 'Spectral');

plt.tight_layout()

4. Season Wise Distribution

# Participants in Winter and Summer Season
Sum = df[df.Season=='Summer']
Win = df[df.Season=='Winter']

sns.set(style="darkgrid")
plt.figure(figsize =(20,12))

plt.subplot(2,1,1)
sns.countplot(x= 'Year', data=Sum, palette= "Spectral")
plt.title('Participants In Summer Season', fontsize=15)

plt.subplot(2,1,2)
sns.countplot(x= 'Year', data=Win, palette= "Spectral")
plt.title('Participants In Winter Season', fontsize=15)

Text(0.5, 1.0, 'Participants In Winter Season')

# Medal in Winter and Summer Season
Sum = dff[dff.Season=='Summer']
Win = dff[dff.Season=='Winter']

sns.set(style="darkgrid")
plt.figure(figsize =(20,12))

plt.subplot(2,1,1)
sns.countplot(x= 'Year', data=Sum, palette= "Spectral")
plt.title('Winners of Medals In Summer Season', fontsize=15)

plt.subplot(2,1,2)
sns.countplot(x= 'Year', data=Win, palette= "Spectral")
plt.title('Winners of Medals In Winter Season', fontsize=15)

Text(0.5, 1.0, 'Winners of Medals In Winter Season')

womenOlympicsSum = dff[(dff.Gender=='F') & (dff.Season=='Summer')]
womenOlympicsWin = dff[(dff.Gender=='F') & (dff.Season=='Winter')]
# womenOlympicsSum.head()

sns.set(style="darkgrid")
plt.figure(figsize =(20,12))

plt.subplot(2,1,1)
sns.countplot(x= 'Year', data=womenOlympicsSum, palette= "Spectral")
sns.lineplot(x='Year', data=womenOlympicsSum, palette='crest')
plt.title('Women Medallist In Summer Season', fontsize=15)

plt.subplot(2,1,2)
sns.countplot(x= 'Year', data=womenOlympicsWin, palette= "Spectral")
plt.title('Women Medallist In Winter Season', fontsize=15)

C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\numpy\lib\nanfunctions.py:1368: RuntimeWarning: All-NaN slice encountered
  r, k = function_base._ureduce(

Text(0.5, 1.0, 'Women Participation In Winter Season')

Variation of Male/Female athletes over Time (Summer Games)

MenOverTimeSum = dff[(dff.Gender == 'M') & (dff.Season == 'Summer')]
WomenOverTimeSum = dff[(dff.Gender == 'F') & (dff.Season == 'Summer')]
MenOverTimeWin = dff[(dff.Gender == 'M') & (dff.Season == 'Winter')]
WomenOverTimeWin = dff[(dff.Gender == 'F') & (dff.Season == 'Winter')]
womenOlympicsSum.head()

	Name	Gender	Age	Height	Weight	NOC	Year	Season	City	Sport	Event	Medal	Region
17	Ragnhild Margrethe Aamodt	F	27	163	70	NOR	2008	Summer	Beijing	Handball	Handball Women's Handball	Gold	Norway
19	Willemien Aardenburg	F	22	175	70	NED	1988	Summer	Seoul	Hockey	Hockey Women's Hockey	Bronze	Netherlands
21	Ann Kristin Aarnes	F	23	182	64	NOR	1996	Summer	Atlanta	Football	Football Women's Football	Bronze	Norway
29	Patimat Abakarova	F	21	165	49	AZE	2016	Summer	Rio de Janeiro	Taekwondo	Taekwondo Women's Flyweight	Bronze	Azerbaijan
30	Mariya Vasilyevna Abakumova (-Tarabina)	F	22	179	80	RUS	2008	Summer	Beijing	Athletics	Athletics Women's Javelin Throw	Silver	Russia

part1 = MenOverTimeSum.groupby('Year')['Gender'].value_counts()
part2 = WomenOverTimeSum.groupby('Year')['Gender'].value_counts()
plt.figure(figsize=(20, 10))
part1.loc[:,'M'].plot(color='r')
part2.loc[:,'F'].plot(color='b')
plt.title('Variation of Male and Female Medallist over time for Summer Olympics', fontsize=15)

Text(0.5, 1.0, 'Variation of Male and Female Medallist over time for Summer Olympics')

part1 = MenOverTimeWin.groupby('Year')['Gender'].value_counts()
part2 = WomenOverTimeWin.groupby('Year')['Gender'].value_counts()
plt.figure(figsize=(20, 10))
part1.loc[:,'M'].plot(color='r')
part2.loc[:,'F'].plot(color='b')
plt.title('Variation of Male and Female Medallist over time for Winter Olympics', fontsize=15)

Text(0.5, 1.0, 'Variation of Male and Female Medallist over time for Winter Olympics')

# part2 = WomenOverTimeSum.groupby('Year')['Gender'].value_counts()
# plt.figure(figsize=(20, 10))
# part2.loc[:,'F'].plot(color='b')
# plt.title('Variation of Female Athletes over time', fontsize=15)

Variation of Male/Female athletes over Time (Winter Games)

MenOverTimeWin = dff[(dff.Gender == 'M') & (dff.Season == 'Winter')]
WomenOverTimeWin = dff[(dff.Gender == 'F') & (dff.Season == 'Winter')]

# part1 = MenOverTimeWin.groupby('Year')['Gender'].value_counts()
# plt.figure(figsize=(20, 10))
# part1.loc[:,'M'].plot(color='r')
# plt.title('Variation of Male Athletes over time', fontsize=15)

# part2 = WomenOverTimeWin.groupby('Year')['Gender'].value_counts()
# plt.figure(figsize=(20, 10))
# part2.loc[:,'F'].plot(color='b')
# plt.title('Variation of Female Athletes over time', fontsize=15)

5 Age & Height Wise Distribution

# Medallist on the basis of Height and Weight
plt.figure(figsize=(20, 10))
ax = sns.scatterplot(x="Height", y="Weight", data=dff, hue="Medal", style="Medal")
plt.title('Height vs Weight of Olympic Medalists', fontsize=25)

Text(0.5, 1.0, 'Height vs Weight of Olympic Medalists')

age_ab_60 = dff[dff.Age>=60]
age_ab_60

	Name	Gender	Age	Height	Weight	NOC	Year	Season	City	Sport	Event	Medal	Region
2904	Rudolf Georg Binding	M	60	175	70	GER	1928	Summer	Amsterdam	Art Competitions	Art Competitions Mixed Literature, Lyric Works	Silver	Germany
4553	John Hurst Butt	M	61	175	70	GBR	1912	Summer	Stockholm	Shooting	Shooting Men's Trap, Team	Silver	United Kingdom
6070	John (Herbert Crawford-) Copley (Williamson-)	M	73	175	70	GBR	1948	Summer	London	Art Competitions	Art Competitions Mixed Painting, Graphic Arts	Silver	United Kingdom
8276	Jozu Dupon	M	72	175	70	BEL	1936	Summer	Berlin	Art Competitions	Art Competitions Mixed Sculpturing, Medals	Bronze	Belgium
8337	Samuel Harding Duvall	M	68	175	70	USA	1904	Summer	St. Louis	Archery	Archery Men's Team Round	Silver	USA
8819	Thodore Lon Epin	M	61	175	70	FRA	1920	Summer	Antwerpen	Archery	Archery Men's Target Archery, 28 metres, Team	Bronze	France
8820	Thodore Lon Epin	M	61	175	70	FRA	1920	Summer	Antwerpen	Archery	Archery Men's Target Archery, 33 metres, Team	Silver	France
8821	Thodore Lon Epin	M	61	175	70	FRA	1920	Summer	Antwerpen	Archery	Archery Men's Target Archery, 50 metres, Team	Silver	France
12608	Letitia Marion Hamilton	F	69	175	70	IRL	1948	Summer	London	Art Competitions	Art Competitions Mixed Painting, Paintings	Bronze	Ireland
14884	Isaac Lazarus Israls	M	63	175	70	NED	1928	Summer	Amsterdam	Art Competitions	Art Competitions Mixed Painting, Paintings	Gold	Netherlands
15048	Charles Jacobus	M	64	175	70	USA	1904	Summer	St. Louis	Roque	Roque Men's Singles	Gold	USA
18914	Josef Maximilian "Max" Laeuger	M	63	175	70	GER	1928	Summer	Amsterdam	Art Competitions	Art Competitions Mixed Architecture, Designs F...	Bronze	Germany
21189	Frederick William MacMonnies	M	68	175	70	USA	1932	Summer	Los Angeles	Art Competitions	Art Competitions Mixed Sculpturing, Medals And...	Silver	USA
21892	Charles William Martin	M	71	175	70	FRA	1900	Summer	Paris	Sailing	Sailing Mixed 0.5-1 Ton	Silver	France
21893	Charles William Martin	M	71	175	70	FRA	1900	Summer	Paris	Sailing	Sailing Mixed 0.5-1 Ton	Bronze	France
22488	Robert Tait McKenzie	M	65	175	70	CAN	1932	Summer	Los Angeles	Art Competitions	Art Competitions Mixed Sculpturing, Medals And...	Bronze	Canada
23117	Ian Millar	M	61	185	76	CAN	2008	Summer	Beijing	Equestrianism	Equestrianism Mixed Jumping, Team	Silver	Canada
23165	Joshua Kearney Millner	M	60	175	70	GBR	1908	Summer	London	Shooting	Shooting Men's Free Rifle, 1,000 Yards	Gold	United Kingdom
23186	William Milne	M	60	175	70	GBR	1912	Summer	Stockholm	Shooting	Shooting Men's Small-Bore Rifle, Any Position,...	Silver	United Kingdom
23187	William Milne	M	60	175	70	GBR	1912	Summer	Stockholm	Shooting	Shooting Men's Small-Bore Rifle, Disappearing ...	Silver	United Kingdom
24498	Josef Carl Peter Neckermann	M	60	183	65	FRG	1972	Summer	Munich	Equestrianism	Equestrianism Mixed Dressage, Individual	Bronze	Germany
24499	Josef Carl Peter Neckermann	M	60	183	65	FRG	1972	Summer	Munich	Equestrianism	Equestrianism Mixed Dressage, Team	Silver	Germany
25155	Louis Noverraz	M	66	179	78	SUI	1968	Summer	Mexico City	Sailing	Sailing Mixed 5.5 metres	Silver	Switzerland
26985	Josef Petersen	M	66	175	70	DEN	1948	Summer	London	Art Competitions	Art Competitions Mixed Literature, Epic Works	Silver	Denmark
27620	Lida Peyton "Eliza" Pollock (McMillen-)	F	63	175	70	USA	1904	Summer	St. Louis	Archery	Archery Women's Double Columbia Round	Bronze	USA
27621	Lida Peyton "Eliza" Pollock (McMillen-)	F	63	175	70	USA	1904	Summer	St. Louis	Archery	Archery Women's Double National Round	Bronze	USA
27622	Lida Peyton "Eliza" Pollock (McMillen-)	F	63	175	70	USA	1904	Summer	St. Louis	Archery	Archery Women's Team Round	Gold	USA
29710	James William George "Bill" Roycroft	M	61	188	72	AUS	1976	Summer	Montreal	Equestrianism	Equestrianism Mixed Three-Day Event, Team	Bronze	Australia
32841	Galen Carter "G. C." Spencer	M	63	165	70	USA	1904	Summer	St. Louis	Archery	Archery Men's Team Round	Gold	USA
33934	Oscar Gomer Swahn	M	60	175	70	SWE	1908	Summer	London	Shooting	Shooting Men's Running Target, Single Shot	Gold	Sweden
33935	Oscar Gomer Swahn	M	60	175	70	SWE	1908	Summer	London	Shooting	Shooting Men's Running Target, Single Shot, Team	Gold	Sweden
33936	Oscar Gomer Swahn	M	60	175	70	SWE	1908	Summer	London	Shooting	Shooting Men's Running Target, Double Shot	Bronze	Sweden
33937	Oscar Gomer Swahn	M	64	175	70	SWE	1912	Summer	Stockholm	Shooting	Shooting Men's Running Target, Single Shot, Team	Gold	Sweden
33938	Oscar Gomer Swahn	M	64	175	70	SWE	1912	Summer	Stockholm	Shooting	Shooting Men's Running Target, Double Shot	Bronze	Sweden
33939	Oscar Gomer Swahn	M	72	175	70	SWE	1920	Summer	Antwerpen	Shooting	Shooting Men's Running Target, Double Shot, Team	Silver	Sweden
34692	Oskar Thiede	M	69	175	70	AUT	1948	Summer	London	Art Competitions	Art Competitions Mixed Sculpturing, Medals And...	Silver	Austria
34845	Lars Einar Vilhelm Thrn	M	60	175	70	SWE	1964	Summer	Tokyo	Sailing	Sailing Mixed 5.5 metres	Silver	Sweden
38236	Robert W. Williams, Jr.	M	63	175	70	USA	1904	Summer	St. Louis	Archery	Archery Men's Double American Round	Silver	USA
38237	Robert W. Williams, Jr.	M	63	175	70	USA	1904	Summer	St. Louis	Archery	Archery Men's Double York Round	Silver	USA
38238	Robert W. Williams, Jr.	M	63	175	70	USA	1904	Summer	St. Louis	Archery	Archery Men's Team Round	Gold	USA
38334	Walter Winans	M	60	175	70	USA	1912	Summer	Stockholm	Art Competitions	Art Competitions Mixed Sculpturing	Gold	USA
38335	Walter Winans	M	60	175	70	USA	1912	Summer	Stockholm	Shooting	Shooting Men's Running Target, Single Shot, Team	Silver	USA

age_ab_60[age_ab_60.Age>=60].Age.count()

42

age_ab_60[['Name','Age','Medal','Sport','Region']]

	Name	Age	Medal	Sport	Region
2904	Rudolf Georg Binding	60	Silver	Art Competitions	Germany
4553	John Hurst Butt	61	Silver	Shooting	United Kingdom
6070	John (Herbert Crawford-) Copley (Williamson-)	73	Silver	Art Competitions	United Kingdom
8276	Jozu Dupon	72	Bronze	Art Competitions	Belgium
8337	Samuel Harding Duvall	68	Silver	Archery	USA
8819	Thodore Lon Epin	61	Bronze	Archery	France
8820	Thodore Lon Epin	61	Silver	Archery	France
8821	Thodore Lon Epin	61	Silver	Archery	France
12608	Letitia Marion Hamilton	69	Bronze	Art Competitions	Ireland
14884	Isaac Lazarus Israls	63	Gold	Art Competitions	Netherlands
15048	Charles Jacobus	64	Gold	Roque	USA
18914	Josef Maximilian "Max" Laeuger	63	Bronze	Art Competitions	Germany
21189	Frederick William MacMonnies	68	Silver	Art Competitions	USA
21892	Charles William Martin	71	Silver	Sailing	France
21893	Charles William Martin	71	Bronze	Sailing	France
22488	Robert Tait McKenzie	65	Bronze	Art Competitions	Canada
23117	Ian Millar	61	Silver	Equestrianism	Canada
23165	Joshua Kearney Millner	60	Gold	Shooting	United Kingdom
23186	William Milne	60	Silver	Shooting	United Kingdom
23187	William Milne	60	Silver	Shooting	United Kingdom
24498	Josef Carl Peter Neckermann	60	Bronze	Equestrianism	Germany
24499	Josef Carl Peter Neckermann	60	Silver	Equestrianism	Germany
25155	Louis Noverraz	66	Silver	Sailing	Switzerland
26985	Josef Petersen	66	Silver	Art Competitions	Denmark
27620	Lida Peyton "Eliza" Pollock (McMillen-)	63	Bronze	Archery	USA
27621	Lida Peyton "Eliza" Pollock (McMillen-)	63	Bronze	Archery	USA
27622	Lida Peyton "Eliza" Pollock (McMillen-)	63	Gold	Archery	USA
29710	James William George "Bill" Roycroft	61	Bronze	Equestrianism	Australia
32841	Galen Carter "G. C." Spencer	63	Gold	Archery	USA
33934	Oscar Gomer Swahn	60	Gold	Shooting	Sweden
33935	Oscar Gomer Swahn	60	Gold	Shooting	Sweden
33936	Oscar Gomer Swahn	60	Bronze	Shooting	Sweden
33937	Oscar Gomer Swahn	64	Gold	Shooting	Sweden
33938	Oscar Gomer Swahn	64	Bronze	Shooting	Sweden
33939	Oscar Gomer Swahn	72	Silver	Shooting	Sweden
34692	Oskar Thiede	69	Silver	Art Competitions	Austria
34845	Lars Einar Vilhelm Thrn	60	Silver	Sailing	Sweden
38236	Robert W. Williams, Jr.	63	Silver	Archery	USA
38237	Robert W. Williams, Jr.	63	Silver	Archery	USA
38238	Robert W. Williams, Jr.	63	Gold	Archery	USA
38334	Walter Winans	60	Gold	Art Competitions	USA
38335	Walter Winans	60	Silver	Shooting	USA

age_un_20 = dff[dff.Age<=20]
age_un_20

	Name	Gender	Age	Height	Weight	NOC	Year	Season	City	Sport	Event	Medal	Region
9	Kjetil Andr Aamodt	M	20	176	85	NOR	1992	Winter	Albertville	Alpine Skiing	Alpine Skiing Men's Super G	Gold	Norway
10	Kjetil Andr Aamodt	M	20	176	85	NOR	1992	Winter	Albertville	Alpine Skiing	Alpine Skiing Men's Giant Slalom	Bronze	Norway
22	Karl Jan Aas	M	20	175	70	NOR	1920	Summer	Antwerpen	Gymnastics	Gymnastics Men's Team All-Around, Free System	Silver	Norway
59	Nia Nicole Abdallah	F	20	175	56	USA	2004	Summer	Athina	Taekwondo	Taekwondo Women's Featherweight	Silver	USA
76	Irene Abel	F	19	160	48	GDR	1972	Summer	Munich	Gymnastics	Gymnastics Women's Team All-Around	Silver	Germany
...	...	...	...	...	...	...	...	...	...	...	...	...	...
39729	Matja Zupan	M	19	179	60	YUG	1988	Winter	Calgary	Ski Jumping	Ski Jumping Men's Large Hill, Team	Silver	Serbia
39733	Albert Hermann Zrner	M	18	175	70	GER	1908	Summer	London	Diving	Diving Men's Springboard	Gold	Germany
39739	Nataliya Vladimirovna Zuyeva	F	19	176	62	RUS	2008	Summer	Beijing	Rhythmic Gymnastics	Rhythmic Gymnastics Women's Group	Gold	Russia
39742	Denis vegelj	M	20	175	70	SLO	1992	Summer	Barcelona	Rowing	Rowing Men's Coxless Pairs	Bronze	Slovenia
39763	Olesya Nikolayevna Zykina	F	19	171	64	RUS	2000	Summer	Sydney	Athletics	Athletics Women's 4 x 400 metres Relay	Bronze	Russia

5411 rows × 13 columns

6. Sports Wise Distribution

# Sports participated in Olympics
s = df.Sport.value_counts().sort_values(ascending=False)
plt.figure(figsize=(20,12))
plt.xticks(rotation=0)

sns.barplot(s, s.index)
plt.show()

C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

# Medals won by Sports
sp = dff.Sport.value_counts().sort_values(ascending=False)
sp

Athletics        3969
Swimming         3048
Rowing           2945
Gymnastics       2256
Fencing          1742
                 ... 
Motorboating        7
Roque               3
Jeu De Paume        3
Basque Pelota       2
Aeronautics         1
Name: Sport, Length: 66, dtype: int64

# Find most
plt.figure(figsize=(20,12))
plt.xticks(rotation=0)

sns.barplot(sp, sp.index)
plt.show()

C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

dff.head()

	Name	Gender	Age	Height	Weight	NOC	Year	Season	City	Sport	Event	Medal	Region
0	Edgar Lindenau Aabye	M	34	175	70	DEN	1900	Summer	Paris	Tug-Of-War	Tug-Of-War Men's Tug-Of-War	Gold	Denmark
1	Arvo Ossian Aaltonen	M	30	175	70	FIN	1920	Summer	Antwerpen	Swimming	Swimming Men's 200 metres Breaststroke	Bronze	Finland
2	Arvo Ossian Aaltonen	M	30	175	70	FIN	1920	Summer	Antwerpen	Swimming	Swimming Men's 400 metres Breaststroke	Bronze	Finland
3	Juhamatti Tapio Aaltonen	M	28	184	85	FIN	2014	Winter	Sochi	Ice Hockey	Ice Hockey Men's Ice Hockey	Bronze	Finland
4	Paavo Johannes Aaltonen	M	28	175	64	FIN	1948	Summer	London	Gymnastics	Gymnastics Men's Individual All-Around	Bronze	Finland

sp_medal = dff[['Sport', 'Medal']]
sp_medal.Medal.value_counts()

Gold      13368
Bronze    13292
Silver    13105
Name: Medal, dtype: int64

g_medal = sp_medal[sp_medal.Medal == 'Gold'].Sport.value_counts().sort_values(ascending=False).head(50)
s_medal = sp_medal[sp_medal.Medal == 'Silver'].Sport.value_counts().sort_values(ascending=False).head(50)
# s_medal
b_medal = sp_medal[sp_medal.Medal == 'Bronze'].Sport.value_counts().sort_values(ascending=False).head(50)
b_medal.head()

Athletics     1296
Rowing         990
Swimming       956
Gymnastics     719
Fencing        566
Name: Sport, dtype: int64

plt.figure(figsize=(20,15))
plt.xticks(rotation=90)

plt.subplot(1,3,1)
plt.title('Won Gold By Top 50 Sports', fontsize=15)
#plt.xlabel('Sports', fontsize=15)
plt.ylabel('Gold Medals', fontsize=15)
sns.barplot(x=g_medal, y=g_medal.index, palette = 'rocket');
#sns.lineplot(x=g_medal, y=g_medal.index, palette = 'crest');

plt.subplot(1,3,2)
plt.title('Won Silver By Top 50 Sports', fontsize=15)
#plt.xlabel('Sports', fontsize=15)
plt.ylabel('Silver Medals', fontsize=15)
sns.barplot(x=s_medal, y=s_medal.index, palette = 'rocket');
#sns.lineplot(x=s_medal, y=s_medal.index, color='b', palette = 'crest');

plt.subplot(1,3,3)
plt.title('Won Bronz By Top 50 Sports', fontsize=15)
plt.xlabel('Sports', fontsize=15)
plt.ylabel('Bronze Medals', fontsize=15)
sns.barplot(x=b_medal, y=b_medal.index, palette = 'rocket');
#sns.lineplot(x=b_medal, y=b_medal.index, color='b', palette = 'crest');

plt.tight_layout()

7 Participants

dff.isnull().sum()
# dff.Name

Name      0
Gender    0
Age       0
Height    0
Weight    0
NOC       0
Year      0
Season    0
City      0
Sport     0
Event     0
Medal     0
Region    0
dtype: int64

participants1 = dfa.Name.value_counts().head(50)

participants2 = dff.Name.value_counts().head(50)
#participants.count()

plt.figure(figsize=(20,25))
plt.xticks(rotation=0)

plt.subplot(2,1,1)
sns.barplot(x = participants1, y = participants1.index, palette="icefire")

plt.subplot(2,1,2)
sns.barplot(x = participants2, y = participants2.index, palette="icefire")

<AxesSubplot:xlabel='Name'>

8 Country Comparison

India

ind = dff[(dff.Region=='India') & (dff.Medal == 'Gold')]
ind

	Name	Gender	Age	Height	Weight	NOC	Year	Season	City	Sport	Event	Medal	Region
492	Shaukat Ali	M	30	175	70	IND	1928	Summer	Amsterdam	Hockey	Hockey Men's Hockey	Gold	India
493	Syed Mushtaq Ali	M	22	165	61	IND	1964	Summer	Tokyo	Hockey	Hockey Men's Hockey	Gold	India
529	Richard James Allen	M	25	172	70	IND	1928	Summer	Amsterdam	Hockey	Hockey Men's Hockey	Gold	India
530	Richard James Allen	M	30	172	70	IND	1932	Summer	Los Angeles	Hockey	Hockey Men's Hockey	Gold	India
531	Richard James Allen	M	34	172	70	IND	1936	Summer	Berlin	Hockey	Hockey Men's Hockey	Gold	India
...	...	...	...	...	...	...	...	...	...	...	...	...	...
33981	Dung Dung Sylvanus	M	31	160	62	IND	1980	Summer	Moskva	Hockey	Hockey Men's Hockey	Gold	India
34365	Carlyle Carrol Tapsell	M	23	182	70	IND	1932	Summer	Los Angeles	Hockey	Hockey Men's Hockey	Gold	India
34366	Carlyle Carrol Tapsell	M	27	182	70	IND	1936	Summer	Berlin	Hockey	Hockey Men's Hockey	Gold	India
36502	Max "Maxie" Vaz	M	25	175	70	IND	1948	Summer	London	Hockey	Hockey Men's Hockey	Gold	India
39131	Sayed Muhammad Yusuf	M	25	175	70	IND	1928	Summer	Amsterdam	Hockey	Hockey Men's Hockey	Gold	India

138 rows × 13 columns

print('Total Gold Medal Wond By Indan Players : ', ind[ind['Medal']=='Gold'].Medal.count())
print('Total Silver Medal Wond By Indan Players : ', ind[ind['Medal']=='Silver'].Medal.count())
print('Total Bronze Medal Wond By Indan Players : ', ind[ind['Medal']=='Bronze'].Medal.count(), '\n')
print('Total Medal Wond By Indan Players : ', ind.Medal.value_counts().sum())
print('Total Participants For Sports Hockey : ', ind[ind['Sport']=='Hockey'].Sport.value_counts().sum())

Total Gold Medal Wond By Indan Players :  138
Total Silver Medal Wond By Indan Players :  0
Total Bronze Medal Wond By Indan Players :  0 

Total Medal Wond By Indan Players :  138
Total Participants For Sports Hockey :  130

ind[ind['Sport']!='Hockey'].head()

	Name	Gender	Age	Height	Weight	NOC	Year	Season	City	Sport	Event	Medal	Region
2905	Abhinav Bindra	M	25	173	70	IND	2008	Summer	Beijing	Shooting	Shooting Men's Air Rifle, 10 metres	Gold	India
31648	Antarge Sherpa	M	25	175	70	IND	1924	Winter	Chamonix	Alpinism	Alpinism Mixed Alpinism	Gold	India
31649	Lhakpa Sherpa	M	25	175	70	IND	1924	Winter	Chamonix	Alpinism	Alpinism Mixed Alpinism	Gold	India
31650	Narbu Sherpa	M	25	175	70	IND	1924	Winter	Chamonix	Alpinism	Alpinism Mixed Alpinism	Gold	India
31651	Pasang Sherpa	M	25	175	70	IND	1924	Winter	Chamonix	Alpinism	Alpinism Mixed Alpinism	Gold	India

United State Of America (USA)

usa = dff[dff.Region=='USA']
usa

	Name	Gender	Age	Height	Weight	NOC	Year	Season	City	Sport	Event	Medal	Region
37	Stephen Anthony Abas	M	26	165	55	USA	2004	Summer	Athina	Wrestling	Wrestling Men's Featherweight, Freestyle	Silver	USA
56	Jeremy Abbott	M	28	175	70	USA	2014	Winter	Sochi	Figure Skating	Figure Skating Mixed Team	Bronze	USA
57	Margaret Ives Abbott (-Dunne)	F	23	175	70	USA	1900	Summer	Paris	Golf	Golf Women's Individual	Gold	USA
58	Monica Cecilia Abbott	F	23	191	88	USA	2008	Summer	Beijing	Softball	Softball Women's Softball	Silver	USA
59	Nia Nicole Abdallah	F	20	175	56	USA	2004	Summer	Athina	Taekwondo	Taekwondo Women's Featherweight	Silver	USA
...	...	...	...	...	...	...	...	...	...	...	...	...	...
39604	Rbert Zimonyi	M	46	170	52	USA	1964	Summer	Tokyo	Rowing	Rowing Men's Coxed Eights	Gold	USA
39620	Albert Conrad "Al" Zirkel	M	19	175	70	USA	1904	Summer	St. Louis	Wrestling	Wrestling Men's Lightweight, Freestyle	Bronze	USA
39637	Kimberley Lyn "Kim" Zmeskal (-Burdette)	F	16	139	36	USA	1992	Summer	Barcelona	Gymnastics	Gymnastics Women's Team All-Around	Bronze	USA
39644	Jacqueline Jean "Jackie" Zoch	F	27	180	76	USA	1976	Summer	Montreal	Rowing	Rowing Women's Coxed Eights	Bronze	USA
39666	Zachary "Zac" Zorn	M	21	193	86	USA	1968	Summer	Mexico City	Swimming	Swimming Men's 4 x 100 metres Freestyle Relay	Gold	USA

5636 rows × 13 columns

print('Total Gold Medal Wond By USA Players : ', usa[usa['Medal']=='Gold'].Medal.count())
print('Total Silver Medal Wond By USA Players : ', usa[usa['Medal']=='Silver'].Medal.count())
print('Total Bronze Medal Wond By USA Players : ', usa[usa['Medal']=='Bronze'].Medal.count(), '\n')
print('Total Medal Wond By USA Players : ', usa.Medal.value_counts().sum())

Total Gold Medal Wond By USA Players :  2638
Total Silver Medal Wond By USA Players :  1640
Total Bronze Medal Wond By USA Players :  1358 

Total Medal Wond By USA Players :  5636

8 GDP wise distribution

#import GDP
dfg = pd.read_csv('GDP1.csv')
#dfg.Region.sort_values(ascending=True).unique()
dfg

	Region	Year	GDP
0	Afghanistan	1992	3.475000e+09
1	Albania	1992	6.521750e+08
2	Algeria	1992	4.800308e+10
3	Andorra	1992	1.210014e+09
4	Angola	1992	9.395000e+09
...	...	...	...
2543	Venezuela	2016	2.790000e+11
2544	Vietnam	2016	2.050000e+11
2545	Yemen	2016	3.131737e+10
2546	Zambia	2016	2.095841e+10
2547	Zimbabwe	2016	2.054868e+10

2548 rows × 3 columns

df.Year.sort_values(ascending=True).unique()

array([1896, 1900, 1904, 1906, 1908, 1912, 1920, 1924, 1928, 1932, 1936,
       1948, 1952, 1956, 1960, 1964, 1968, 1972, 1976, 1980, 1984, 1988,
       1992, 1994, 1996, 1998, 2000, 2002, 2004, 2006, 2008, 2010, 2012,
       2014, 2016], dtype=int64)

df_new = df.loc[df.Year.isin([1992,1994,1996,1998,2000,2002,2004,2006,2008,2010,2012,2014,2016])]
df_new.isnull().sum()

Name           0
Gender         0
Age            0
Height         0
Weight         0
NOC            0
Year           0
Season         0
City           0
Sport          0
Event          0
Medal     105431
Region         0
dtype: int64

df_new = df_new.merge(dfg, on=['Region','Year'], how='left')
df_new.isnull().sum()

Name           0
Gender         0
Age            0
Height         0
Weight         0
NOC            0
Year           0
Season         0
City           0
Sport          0
Event          0
Medal     105431
Region         0
GDP         1187
dtype: int64

#df_new[df_new.isnull().any(axis=1)]
df_new[df_new.GDP.isnull()]

	Name	Gender	Age	Height	Weight	NOC	Year	Season	City	Sport	Event	Medal	Region	GDP
253	Hamza Abdo	M	17	175	70	PLE	2008	Summer	Beijing	Swimming	Swimming Men's 50 metres Freestyle	NaN	Palestine	NaN
376	Julianne "Anne" Abernathy	F	38	165	75	ISV	1992	Winter	Albertville	Luge	Luge Women's Singles	NaN	Virgin Islands, US	NaN
377	Julianne "Anne" Abernathy	F	40	165	75	ISV	1994	Winter	Lillehammer	Luge	Luge Women's Singles	NaN	Virgin Islands, US	NaN
378	Julianne "Anne" Abernathy	F	44	165	75	ISV	1998	Winter	Nagano	Luge	Luge Women's Singles	NaN	Virgin Islands, US	NaN
379	Julianne "Anne" Abernathy	F	48	165	75	ISV	2002	Winter	Salt Lake City	Luge	Luge Women's Singles	NaN	Virgin Islands, US	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
121765	Zachary John Zoller	M	21	178	98	ISV	1994	Winter	Lillehammer	Bobsleigh	Bobsleigh Men's Two	NaN	Virgin Islands, US	NaN
121766	Zachary John Zoller	M	21	178	98	ISV	1994	Winter	Lillehammer	Bobsleigh	Bobsleigh Men's Four	NaN	Virgin Islands, US	NaN
121767	Zachary John Zoller	M	25	178	98	ISV	1998	Winter	Nagano	Bobsleigh	Bobsleigh Men's Two	NaN	Virgin Islands, US	NaN
121768	Zachary John Zoller	M	29	178	98	ISV	2002	Winter	Salt Lake City	Bobsleigh	Bobsleigh Men's Two	NaN	Virgin Islands, US	NaN
121799	Stevan Zori	M	21	199	75	IOA	1992	Summer	Barcelona	Athletics	Athletics Men's High Jump	NaN	Individual Olympic Athletes	NaN

1187 rows × 14 columns

#dfg.Region.sort_values(ascending=True).unique()

#df_new.Region.sort_values(ascending=True).unique()

df_new = df_new[df_new['GDP'].notna()]

df_new.isnull().sum()

Name           0
Gender         0
Age            0
Height         0
Weight         0
NOC            0
Year           0
Season         0
City           0
Sport          0
Event          0
Medal     104296
Region         0
GDP            0
dtype: int64

df_new.shape

(121023, 14)

df_new.isnull().sum()
dfm = df_new.dropna()
dfm.isnull().sum()

Name      0
Gender    0
Age       0
Height    0
Weight    0
NOC       0
Year      0
Season    0
City      0
Sport     0
Event     0
Medal     0
Region    0
GDP       0
dtype: int64

dfm.reset_index(drop=True,inplace=True)
dfm

	Name	Gender	Age	Height	Weight	NOC	Year	Season	City	Sport	Event	Medal	Region	GDP
0	Juhamatti Tapio Aaltonen	M	28	184	85	FIN	2014	Winter	Sochi	Ice Hockey	Ice Hockey Men's Ice Hockey	Bronze	Finland	2.740000e+11
1	Kjetil Andr Aamodt	M	20	176	85	NOR	1992	Winter	Albertville	Alpine Skiing	Alpine Skiing Men's Super G	Gold	Norway	1.310000e+11
2	Kjetil Andr Aamodt	M	20	176	85	NOR	1992	Winter	Albertville	Alpine Skiing	Alpine Skiing Men's Giant Slalom	Bronze	Norway	1.310000e+11
3	Kjetil Andr Aamodt	M	22	176	85	NOR	1994	Winter	Lillehammer	Alpine Skiing	Alpine Skiing Men's Downhill	Silver	Norway	1.270000e+11
4	Kjetil Andr Aamodt	M	22	176	85	NOR	1994	Winter	Lillehammer	Alpine Skiing	Alpine Skiing Men's Super G	Bronze	Norway	1.270000e+11
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
16722	Claudia Antoinette Zwiers	F	22	181	78	NED	1996	Summer	Atlanta	Judo	Judo Women's Middleweight	Bronze	Netherlands	4.500000e+11
16723	Henk Jan Zwolle	M	27	197	93	NED	1992	Summer	Barcelona	Rowing	Rowing Men's Double Sculls	Bronze	Netherlands	3.630000e+11
16724	Henk Jan Zwolle	M	31	197	93	NED	1996	Summer	Atlanta	Rowing	Rowing Men's Coxed Eights	Gold	Netherlands	4.500000e+11
16725	Olesya Nikolayevna Zykina	F	19	171	64	RUS	2000	Summer	Sydney	Athletics	Athletics Women's 4 x 400 metres Relay	Bronze	Russia	2.600000e+11
16726	Olesya Nikolayevna Zykina	F	23	171	64	RUS	2004	Summer	Athina	Athletics	Athletics Women's 4 x 400 metres Relay	Silver	Russia	5.910000e+11

16727 rows × 14 columns

# dfm.to_csv("dfg.csv")

X = dfm[(dfm["Year"]==2016) & dfm["Region"]].sort_values(by='GDP',ascending=False)
# X

plt.figure(figsize=(15,15))
plt.xticks(rotation=0)


a = X.Region
b = X.GDP
c = X.Region.value_counts()

plt.subplot(1,2,1)
plt.title('Country-GDP Distribution',fontsize=15)
plt.xlabel('Countries', fontsize=15)
plt.ylabel("GDP", fontsize=15)
sns.barplot(X.GDP, X.Region, palette = 'rocket');



plt.subplot(1,2,2)
plt.title('Country won Medals Distribution',fontsize=15)
plt.xlabel('No. of Medals', fontsize=15)
#plt.ylabel("Region", fontsize=15)
sns.barplot(c, c.index, palette = 'rocket');

plt.tight_layout()

C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(
C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

X1 = dfm[(dfm["Year"]==2014) & dfm["Region"]].sort_values(by='GDP',ascending=False)
X1.Region.unique()

array(['USA', 'China', 'Japan', 'Germany', 'United Kingdom', 'France',
       'Italy', 'Russia', 'Canada', 'South Korea', 'Australia',
       'Netherlands', 'Switzerland', 'Sweden', 'Poland', 'Norway',
       'Austria', 'Finland', 'Kazakhstan', 'Czech Republic', 'Ukraine',
       'Slovakia', 'Belarus', 'Croatia', 'Slovenia', 'Latvia'],
      dtype=object)

plt.figure(figsize=(15,15))
plt.xticks(rotation=0)


a = X1.Region
b = X1.GDP
c = X1.Region.value_counts()

plt.subplot(1,2,1)
plt.title('Country-GDP Distribution',fontsize=15)
plt.xlabel('Countries', fontsize=15)
plt.ylabel("GDP", fontsize=15)
sns.barplot(X1.GDP, X1.Region, palette = 'rocket');



plt.subplot(1,2,2)
plt.title('Country won Medals Distribution',fontsize=15)
plt.xlabel('No. of Medals', fontsize=15)
#plt.ylabel("Region", fontsize=15)
sns.barplot(c, c.index, palette = 'rocket');

plt.tight_layout()

C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(
C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

dfm[(dfm["Year"]==1996) & (dfm["Region"]=="USA")]

	Name	Gender	Age	Height	Weight	NOC	Year	Season	City	Sport	Event	Medal	Region	GDP
100	Derrick Ralph Adkins	M	26	188	80	USA	1996	Summer	Atlanta	Athletics	Athletics Men's 400 metres Hurdles	Gold	USA	2.051554e+10
125	Andre Kirk Agassi	M	26	180	80	USA	1996	Summer	Atlanta	Tennis	Tennis Men's Singles	Gold	USA	2.051554e+10
188	Michelle Anne Akers	F	30	178	68	USA	1996	Summer	Atlanta	Football	Football Women's Football	Gold	USA	2.051554e+10
271	John Chad Allen	M	21	185	86	USA	1996	Summer	Atlanta	Baseball	Baseball Men's Baseball	Bronze	USA	2.051554e+10
443	Kurt Steven Angle	M	27	178	100	USA	1996	Summer	Atlanta	Wrestling	Wrestling Men's Heavyweight, Freestyle	Gold	USA	2.051554e+10
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
15921	Christa Lee Williams	F	18	172	72	USA	1996	Summer	Atlanta	Softball	Softball Women's Softball	Gold	USA	2.051554e+10
15928	Jason Gerald Williams	M	21	172	82	USA	1996	Summer	Atlanta	Baseball	Baseball Men's Baseball	Bronze	USA	2.051554e+10
15976	Linetta A. Wilson	F	28	170	65	USA	1996	Summer	Atlanta	Athletics	Athletics Women's 4 x 400 metres Relay	Gold	USA	2.051554e+10
15984	Staci Nicole Wilson	F	20	158	52	USA	1996	Summer	Atlanta	Football	Football Women's Football	Gold	USA	2.051554e+10
16351	Timothy Paul "Tim" Young	M	28	193	94	USA	1996	Summer	Atlanta	Rowing	Rowing Men's Quadruple Sculls	Silver	USA	2.051554e+10

259 rows × 14 columns

X2 = dfm[(dfm["Year"]==2012) & dfm["Region"]].sort_values(by='GDP',ascending=False)
plt.figure(figsize=(15,15))
plt.xticks(rotation=0)


a = X2.Region
b = X2.GDP
c = X2.Region.value_counts()

plt.subplot(1,2,1)
plt.title('Country-GDP Distribution',fontsize=15)
plt.xlabel('Countries', fontsize=15)
plt.ylabel("GDP", fontsize=15)
sns.barplot(X2.GDP, X2.Region, palette = 'rocket');



plt.subplot(1,2,2)
plt.title('Country won Medals Distribution',fontsize=15)
plt.xlabel('No. of Medals', fontsize=15)
#plt.ylabel("Region", fontsize=15)
sns.barplot(c, c.index, palette = 'rocket');

plt.tight_layout()

C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(
C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

X3 = dfm[(dfm["Year"]==1992) & dfm["Region"]].sort_values(by='GDP',ascending=False)
plt.figure(figsize=(15,15))
plt.xticks(rotation=0)


a = X3.Region
b = X3.GDP
c = X3.Region.value_counts()

plt.subplot(1,2,1)
plt.title('Country-GDP Distribution',fontsize=15)
plt.xlabel('Countries', fontsize=15)
plt.ylabel("GDP", fontsize=15)
sns.barplot(X3.GDP, X3.Region, palette = 'rocket');



plt.subplot(1,2,2)
plt.title('Country won Medals Distribution',fontsize=15)
plt.xlabel('No. of Medals', fontsize=15)
#plt.ylabel("Region", fontsize=15)
sns.barplot(c, c.index, palette = 'rocket');

plt.tight_layout()

C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(
C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

Data Preprocessing

df_new.columns

Index(['Name', 'Gender', 'Age', 'Height', 'Weight', 'NOC', 'Year', 'Season',
       'City', 'Sport', 'Event', 'Medal', 'Region', 'GDP'],
      dtype='object')

# Select Required columns
dfn = df_new[['Gender', 'Age', 'Height', 'Weight', 'Season', 'Sport', 'Medal', 'Region','GDP']]
dfn.head()

	Gender	Age	Height	Weight	Season	Sport	Medal	Region	GDP
0	M	24	180	80	Summer	Basketball	NaN	China	4.270000e+11
1	M	23	170	60	Summer	Judo	NaN	China	8.530000e+12
2	F	25	185	82	Winter	Speed Skating	NaN	Netherlands	3.630000e+11
3	F	25	185	82	Winter	Speed Skating	NaN	Netherlands	3.630000e+11
4	F	27	185	82	Winter	Speed Skating	NaN	Netherlands	3.790000e+11

le = LabelEncoder()
dfn['Gender']= le.fit_transform(dfn['Gender'])

dfn['Gender'].unique()

C:\Users\SHUBHA~1\AppData\Local\Temp/ipykernel_10964/3242760647.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  dfn['Gender']= le.fit_transform(dfn['Gender'])

array([1, 0])

print('Male =', 1, '\nFemale =', 0)

Male = 1 
Female = 0

dfn.Season.unique()

array(['Summer', 'Winter'], dtype=object)

dfn['Season']= le.fit_transform(dfn['Season'])

C:\Users\SHUBHA~1\AppData\Local\Temp/ipykernel_10964/994204159.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  dfn['Season']= le.fit_transform(dfn['Season'])

print('\n 0 = Summer \n 1 = Winter')

 0 = Summer 
 1 = Winter

dfn.Medal.fillna('No Medal', inplace=True)
#dfn

C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\pandas\core\generic.py:6392: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  return self._update_inplace(result)

dfn.Medal.value_counts()

No Medal    104296
Bronze        5734
Gold          5530
Silver        5463
Name: Medal, dtype: int64

dfn['Medal'].replace({'Gold' : 1, 'Silver' :  1, 'Bronze' : 1, 'No Medal' : 0}, inplace = True)

C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\pandas\core\generic.py:6619: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  return self._update_inplace(result)

dfn.Medal.value_counts()

0    104296
1     16727
Name: Medal, dtype: int64

# dfn['Sport']= le.fit_transform(dfn['Sport'])
# dfn['Region'] = le.fit_transform(dfn['Region'])
dfn = pd.get_dummies(dfn, columns = ['Sport', 'Region'])

dfn

	Gender	Age	Height	Weight	Season	Medal	GDP	Sport_Alpine Skiing	Sport_Archery	Sport_Athletics	...	Region_United Arab Emirates	Region_United Kingdom	Region_Uruguay	Region_Uzbekistan	Region_Vanuatu	Region_Venezuela	Region_Vietnam	Region_Yemen	Region_Zambia	Region_Zimbabwe
0	1	24	180	80	0	0	4.270000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
1	1	23	170	60	0	0	8.530000e+12	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2	0	25	185	82	1	0	3.630000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
3	0	25	185	82	1	0	3.630000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
4	0	27	185	82	1	0	3.790000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
122205	0	33	171	69	0	0	4.772266e+10	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122206	1	27	176	59	1	0	5.420000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122207	1	27	176	59	1	0	5.420000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122208	1	30	185	96	1	0	1.750000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122209	1	34	185	96	1	0	1.990000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0

121023 rows × 253 columns

#dfn.Region.sort_values(ascending=True).unique()

# dfn.Sport.sort_values(ascending=True).unique()

Remove Outliers

Q1 = dfn.Height.quantile(0.25)
Q3 = dfn.Height.quantile(0.75)
Q1, Q3

(169.0, 183.0)

IQR = Q3 - Q1
IQR

14.0

lower_limit = Q1-1.5*IQR
upper_limit = Q3+1.5*IQR
lower_limit, upper_limit

(148.0, 204.0)

dfn = dfn[(dfn.Height>148) & (dfn.Height<204)]
dfn

	Gender	Age	Height	Weight	Season	Medal	GDP	Sport_Alpine Skiing	Sport_Archery	Sport_Athletics	...	Region_United Arab Emirates	Region_United Kingdom	Region_Uruguay	Region_Uzbekistan	Region_Vanuatu	Region_Venezuela	Region_Vietnam	Region_Yemen	Region_Zambia	Region_Zimbabwe
0	1	24	180	80	0	0	4.270000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
1	1	23	170	60	0	0	8.530000e+12	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2	0	25	185	82	1	0	3.630000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
3	0	25	185	82	1	0	3.630000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
4	0	27	185	82	1	0	3.790000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
122205	0	33	171	69	0	0	4.772266e+10	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122206	1	27	176	59	1	0	5.420000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122207	1	27	176	59	1	0	5.420000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122208	1	30	185	96	1	0	1.750000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122209	1	34	185	96	1	0	1.990000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0

119527 rows × 253 columns

dfn.shape

(119527, 253)

q1 = dfn.Age.quantile(0.25)
q3 = dfn.Age.quantile(0.75)
q1,q3

(22.0, 28.0)

IQR = q3-q1
IQR

6.0

lower_limit = q1-1.5*IQR
upper_limit = q3+1.5*IQR
lower_limit, upper_limit

(13.0, 37.0)

dfn = dfn[(dfn.Age>13) & (dfn.Age<37)]
dfn

	Gender	Age	Height	Weight	Season	Medal	GDP	Sport_Alpine Skiing	Sport_Archery	Sport_Athletics	...	Region_United Arab Emirates	Region_United Kingdom	Region_Uruguay	Region_Uzbekistan	Region_Vanuatu	Region_Venezuela	Region_Vietnam	Region_Yemen	Region_Zambia	Region_Zimbabwe
0	1	24	180	80	0	0	4.270000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
1	1	23	170	60	0	0	8.530000e+12	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2	0	25	185	82	1	0	3.630000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
3	0	25	185	82	1	0	3.630000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
4	0	27	185	82	1	0	3.790000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
122205	0	33	171	69	0	0	4.772266e+10	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122206	1	27	176	59	1	0	5.420000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122207	1	27	176	59	1	0	5.420000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122208	1	30	185	96	1	0	1.750000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122209	1	34	185	96	1	0	1.990000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0

115490 rows × 253 columns

Q1 = dfn.Weight.quantile(0.25)
Q3 = dfn.Weight.quantile(0.75)
Q1, Q3

(61.0, 79.0)

IQR = Q3 - Q1
IQR

18.0

lower_limit = Q1-1.5*IQR
upper_limit = Q3+1.5*IQR
lower_limit, upper_limit

(34.0, 106.0)

dfn = dfn[(dfn.Weight>34) & (dfn.Weight<106)]
dfn

	Gender	Age	Height	Weight	Season	Medal	GDP	Sport_Alpine Skiing	Sport_Archery	Sport_Athletics	...	Region_United Arab Emirates	Region_United Kingdom	Region_Uruguay	Region_Uzbekistan	Region_Vanuatu	Region_Venezuela	Region_Vietnam	Region_Yemen	Region_Zambia	Region_Zimbabwe
0	1	24	180	80	0	0	4.270000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
1	1	23	170	60	0	0	8.530000e+12	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2	0	25	185	82	1	0	3.630000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
3	0	25	185	82	1	0	3.630000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
4	0	27	185	82	1	0	3.790000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
122205	0	33	171	69	0	0	4.772266e+10	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122206	1	27	176	59	1	0	5.420000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122207	1	27	176	59	1	0	5.420000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122208	1	30	185	96	1	0	1.750000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122209	1	34	185	96	1	0	1.990000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0

113607 rows × 253 columns

plt.figure(figsize=(20,8))
sns.boxplot(x=dfn['GDP'])

<AxesSubplot:xlabel='GDP'>

Q1 = dfn.GDP.quantile(0.25)
Q3 = dfn.GDP.quantile(0.75)
Q1, Q3

(70750646248.0, 1550000000000.0)

IQR = Q3-Q1
IQR

1479249353752.0

lower_limit = Q1-1.5*IQR
upper_limit = Q3+1.5*IQR
lower_limit, upper_limit

(-2148123384380.0, 3768874030628.0)

dfn = dfn[(dfn.GDP>lower_limit) & (dfn.GDP<upper_limit)]
dfn

	Gender	Age	Height	Weight	Season	Medal	GDP	Sport_Alpine Skiing	Sport_Archery	Sport_Athletics	...	Region_United Arab Emirates	Region_United Kingdom	Region_Uruguay	Region_Uzbekistan	Region_Vanuatu	Region_Venezuela	Region_Vietnam	Region_Yemen	Region_Zambia	Region_Zimbabwe
0	1	24	180	80	0	0	4.270000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2	0	25	185	82	1	0	3.630000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
3	0	25	185	82	1	0	3.630000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
4	0	27	185	82	1	0	3.790000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
5	0	27	185	82	1	0	3.790000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
122205	0	33	171	69	0	0	4.772266e+10	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122206	1	27	176	59	1	0	5.420000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122207	1	27	176	59	1	0	5.420000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122208	1	30	185	96	1	0	1.750000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
122209	1	34	185	96	1	0	1.990000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0

102978 rows × 253 columns

dfn.reset_index(drop=True, inplace=True)
dfn

	Gender	Age	Height	Weight	Season	Medal	GDP	Sport_Alpine Skiing	Sport_Archery	Sport_Athletics	...	Region_United Arab Emirates	Region_United Kingdom	Region_Uruguay	Region_Uzbekistan	Region_Vanuatu	Region_Venezuela	Region_Vietnam	Region_Yemen	Region_Zambia	Region_Zimbabwe
0	1	24	180	80	0	0	4.270000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
1	0	25	185	82	1	0	3.630000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2	0	25	185	82	1	0	3.630000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
3	0	27	185	82	1	0	3.790000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
4	0	27	185	82	1	0	3.790000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
102973	0	33	171	69	0	0	4.772266e+10	0	0	0	...	0	0	0	0	0	0	0	0	0	0
102974	1	27	176	59	1	0	5.420000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
102975	1	27	176	59	1	0	5.420000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
102976	1	30	185	96	1	0	1.750000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0
102977	1	34	185	96	1	0	1.990000e+11	0	0	0	...	0	0	0	0	0	0	0	0	0	0

102978 rows × 253 columns

#dfn.isnull().sum().sum()

# dfn.to_csv("Olympics_cd.csv")

dfn.Medal.value_counts()

0    89748
1    13230
Name: Medal, dtype: int64

(13230/89748)*100

14.741275571600482

dfn.corr()

	Gender	Age	Height	Weight	Season	Medal	GDP	Sport_Alpine Skiing	Sport_Archery	Sport_Athletics	...	Region_United Arab Emirates	Region_United Kingdom	Region_Uruguay	Region_Uzbekistan	Region_Vanuatu	Region_Venezuela	Region_Vietnam	Region_Yemen	Region_Zambia	Region_Zimbabwe
Gender	1.000000	0.116824	0.516327	0.557537	0.020024	-0.021660	-0.061476	-0.012775	-0.020989	-0.045620	...	0.019204	-0.014588	0.013612	0.011263	0.000924	0.009346	-0.013892	0.009843	0.006789	-0.003218
Age	0.116824	1.000000	0.139449	0.182736	0.028761	0.058578	0.075329	-0.046922	-0.007448	0.068540	...	-0.012310	0.020886	-0.000347	-0.010417	-0.007154	-0.002279	-0.013943	-0.015111	-0.008808	-0.003188
Height	0.516327	0.139449	1.000000	0.807725	-0.036120	0.066216	0.020359	-0.022114	-0.020003	-0.014790	...	-0.008307	0.011964	0.005970	-0.001594	-0.010261	-0.009997	-0.025962	-0.011270	-0.007074	-0.007446
Weight	0.557537	0.182736	0.807725	1.000000	0.025804	0.073357	-0.000137	0.062148	-0.001070	-0.113480	...	-0.005769	0.013114	0.007035	-0.000340	-0.007697	-0.000391	-0.027519	-0.011578	-0.007744	-0.010695
Season	0.020024	0.028761	-0.036120	0.025804	1.000000	-0.029097	0.004989	0.363560	-0.058589	-0.217767	...	-0.016316	-0.048054	-0.016224	-0.026466	-0.008984	-0.036832	-0.016131	-0.009781	-0.012824	-0.019457
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
Region_Venezuela	0.009346	-0.002279	-0.009997	-0.000391	-0.036832	-0.023200	-0.037297	-0.013758	-0.000359	-0.008279	...	-0.002006	-0.012803	-0.001995	-0.004565	-0.001105	1.000000	-0.001984	-0.001203	-0.001577	-0.002544
Region_Vietnam	-0.013892	-0.013943	-0.025962	-0.027519	-0.016131	-0.009167	-0.019853	-0.005865	-0.003071	0.006273	...	-0.000855	-0.005458	-0.000850	-0.001946	-0.000471	-0.001984	1.000000	-0.000513	-0.000672	-0.001084
Region_Yemen	0.009843	-0.015111	-0.011270	-0.011578	-0.009781	-0.006769	-0.014018	-0.003556	-0.001862	0.015756	...	-0.000519	-0.003309	-0.000516	-0.001180	-0.000286	-0.001203	-0.000513	1.000000	-0.000408	-0.000657
Region_Zambia	0.006789	-0.008808	-0.007074	-0.007744	-0.012824	-0.007619	-0.018580	-0.004662	-0.002441	0.020582	...	-0.000680	-0.004339	-0.000676	-0.001547	-0.000374	-0.001577	-0.000672	-0.000408	1.000000	-0.000862
Region_Zimbabwe	-0.003218	-0.003188	-0.007446	-0.010695	-0.019457	-0.008862	-0.029998	-0.004830	-0.003938	0.026761	...	-0.001097	-0.006999	-0.001091	-0.002495	-0.000604	-0.002544	-0.001084	-0.000657	-0.000862	1.000000

253 rows × 253 columns

y = dfn['Medal']

x = dfn.drop(columns=["Medal"], axis=1)

x

	Gender	Age	Height	Weight	Season	GDP	Sport_Alpine Skiing	Sport_Archery	Sport_Athletics	Sport_Badminton	...	Region_United Arab Emirates	Region_United Kingdom	Region_Uruguay	Region_Uzbekistan	Region_Vanuatu	Region_Venezuela	Region_Vietnam	Region_Yemen	Region_Zambia	Region_Zimbabwe
0	1	24	180	80	0	4.270000e+11	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
1	0	25	185	82	1	3.630000e+11	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2	0	25	185	82	1	3.630000e+11	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
3	0	27	185	82	1	3.790000e+11	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
4	0	27	185	82	1	3.790000e+11	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
102973	0	33	171	69	0	4.772266e+10	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
102974	1	27	176	59	1	5.420000e+11	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
102975	1	27	176	59	1	5.420000e+11	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
102976	1	30	185	96	1	1.750000e+11	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
102977	1	34	185	96	1	1.990000e+11	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0

102978 rows × 252 columns

y

0         0
1         0
2         0
3         0
4         0
         ..
102973    0
102974    0
102975    0
102976    0
102977    0
Name: Medal, Length: 102978, dtype: int64

Data Standardization

sc = StandardScaler()

x = sc.fit_transform(x)

x.shape

(102978, 252)

# pca = PCA(n_components=2)
# x = pca.fit_transform(x)
# print(pca.explained_variance_ratio_)

# #Explained variance
# pca = PCA().fit(x)
# plt.figure(figsize=(12,6))
# plt.plot(np.cumsum(pca.explained_variance_ratio_))
# plt.xlabel('number of components')
# plt.ylabel('cumulative explained variance')
# plt.show()

x.shape

(102978, 252)

Train Test Splitting

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=0)

# x_train
# y_train
# x_test
# y_test
print('Total no. of samples: Training and Testing dataset separately!')
print('x_train:', np.shape(x_train))
print('y_train:', np.shape(y_train))
print('x_test:', np.shape(x_test))
print('y_test:', np.shape(y_test))

Total no. of samples: Training and Testing dataset separately!
x_train: (82382, 252)
y_train: (82382,)
x_test: (20596, 252)
y_test: (20596,)

Logistic Regression

classifier = LogisticRegression()
classifier.fit(x_train,y_train)

LogisticRegression()

y_pred = classifier.predict(x_test)
print(y_pred)

[0 0 0 ... 0 0 0]

count=0
for i in y_pred:
    if i == 1:
        count+=1
    #count += 1
print(count)

31

#from sklearn.metrics import r2_score
result1 = accuracy_score(y_test,y_pred)
print ('R Squared =',r2_score(y_test, y_pred))
print("Accuracy:  ",result1*100,"%")

R Squared = -0.14950391005536345
Accuracy:   87.02175179646532 %

# logreg=accuracy_score(y_test,y_pred)
# logreg

cm = confusion_matrix(y_test, y_pred)
print(cm)

[[17908    16]
 [ 2657    15]]

ax = sns.heatmap(cm, annot=True, cmap='Blues')

#ax.set_title('Seaborn Confusion Matrix with labels\n\n');
ax.set_xlabel('Predicted Values')
ax.set_ylabel('Actual Values');

## Ticket labels - List must be in alphabetical order
ax.xaxis.set_ticklabels(['False','True'])
ax.yaxis.set_ticklabels(['False','True'])

## Display the visualization of the Confusion Matrix.
plt.show()

print(classifier.score(x_train, y_train))
print(classifier.score(x_test, y_test))

0.8716224417955378
0.8702175179646533

mae_lr = round(metrics.mean_absolute_error(y_test, y_pred), 4)
print(mae_lr)
mse_lr = round(metrics.mean_squared_error(y_test, y_pred), 4)
print(mse_lr)

0.1298
0.1298

roc_auc_score(y_test, y_pred)

0.5023605572831129

import sklearn.metrics as metrics
print(metrics.classification_report(y_test, y_pred))

              precision    recall  f1-score   support

           0       0.87      1.00      0.93     17924
           1       0.48      0.01      0.01      2672

    accuracy                           0.87     20596
   macro avg       0.68      0.50      0.47     20596
weighted avg       0.82      0.87      0.81     20596

Support Vector Machine

classifier_svm = SVC(kernel='linear', random_state=0)  
classifier_svm.fit(x_train, y_train)

#Predicting the test set result  
y_pred= classifier_svm.predict(x_test)
y_pred

#Creating the Confusion matrix  
#from sklearn.metrics import confusion_matrix  
cmat= confusion_matrix(y_test, y_pred)
cmat

ax = sns.heatmap(cmat, annot=True, cmap='Blues')

#ax.set_title('Seaborn Confusion Matrix with labels\n\n');
ax.set_xlabel('Predicted Values')
ax.set_ylabel('Actual Values');

## Ticket labels - List must be in alphabetical order
ax.xaxis.set_ticklabels(['False','True'])
ax.yaxis.set_ticklabels(['False','True'])

## Display the visualization of the Confusion Matrix.
plt.show()

#from sklearn.metrics import r2_score
result2 = accuracy_score(y_test,y_pred)
print ('R Squared =',r2_score(y_test, y_pred))
print("Accuracy:  ",result2*100,"%")

# svm_score = round(classifier.score(x_test, y_test), 4)
# svm_score

mae_svm = round(metrics.mean_absolute_error(y_test, y_pred), 4)
mae_svm

0.1227

mse_svm = round(metrics.mean_squared_error(y_test, y_pred), 4)
mse_svm

0.1227

# svm_acc=accuracy_score(y_test,y_pred)
# svm_acc

roc_auc_score(y_test, y_pred)

0.5

import sklearn.metrics as metrics
print(metrics.classification_report(y_test, y_pred))

              precision    recall  f1-score   support

           0       0.88      1.00      0.93      9027
           1       0.00      0.00      0.00      1263

    accuracy                           0.88     10290
   macro avg       0.44      0.50      0.47     10290
weighted avg       0.77      0.88      0.82     10290

C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\sklearn\metrics\_classification.py:1248: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\sklearn\metrics\_classification.py:1248: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\sklearn\metrics\_classification.py:1248: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

K-Nearest Neighbor

knn = KNeighborsClassifier(n_neighbors = 7)
knn.fit(x_train, y_train)

KNeighborsClassifier(n_neighbors=7)

y_pred = knn.predict(x_test)
y_pred

array([0, 0, 0, ..., 0, 0, 0], dtype=int64)

cmatKnn= confusion_matrix(y_test, y_pred)
cmatKnn

array([[17237,   687],
       [ 1653,  1019]], dtype=int64)

ax = sns.heatmap(cmatKnn, annot=True, cmap='Blues')

#ax.set_title('Seaborn Confusion Matrix with labels\n\n');
ax.set_xlabel('Predicted Values')
ax.set_ylabel('Actual Values');

## Ticket labels - List must be in alphabetical order
ax.xaxis.set_ticklabels(['False','True'])
ax.yaxis.set_ticklabels(['False','True'])

## Display the visualization of the Confusion Matrix.
plt.show()

KNN = round(knn.score(x_test, y_test), 6)
KNN

0.886386

mae_knn = metrics.mean_absolute_error(y_test, y_pred)
mae_knn

0.11361429403767721

mse_knn = metrics.mean_squared_error(y_test, y_pred)
mse_knn

0.11361429403767721

compare_models = pd.DataFrame(
    {  'Model' : ['LogReg', 'KNN', 'SVM'],
       'Score' : [result1, KNN, svm_score],
        'MAE'  : [mae_lr, mae_knn, mae_svm],
        'MSE'  : [mse_lr, mse_knn, mse_svm]
    })
  
print(compare_models)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
C:\Users\SHUBHA~1\AppData\Local\Temp/ipykernel_8552/634256479.py in <module>
      1 compare_models = pd.DataFrame(
      2     {  'Model' : ['LogReg', 'KNN', 'SVM'],
----> 3        'Score' : [result1, KNN, svm_score],
      4         'MAE'  : [mae_lr, mae_knn, mae_svm],
      5         'MSE'  : [mse_lr, mse_knn, mse_svm]

NameError: name 'svm_score' is not defined

Decision Tree

classifierDT= DecisionTreeClassifier(criterion='entropy', random_state=0)  
classifierDT.fit(x_train, y_train)

DecisionTreeClassifier(criterion='entropy', random_state=0)

#Predicting the test set result  
y_pred= classifierDT.predict(x_test)
y_pred

array([0, 0, 0, ..., 1, 0, 1], dtype=int64)

#Creating the Confusion matrix  
#from sklearn.metrics import confusion_matrix  
cmDT= confusion_matrix(y_test, y_pred)
cmDT

array([[8193,  834],
       [ 974,  289]], dtype=int64)

ax = sns.heatmap(cmDT, annot=True, cmap='Blues')

#ax.set_title('Seaborn Confusion Matrix with labels\n\n');
ax.set_xlabel('Predicted Values')
ax.set_ylabel('Actual Values');

## Ticket labels - List must be in alphabetical order
ax.xaxis.set_ticklabels(['False','True'])
ax.yaxis.set_ticklabels(['False','True'])

## Display the visualization of the Confusion Matrix.
plt.show()

resultdt = accuracy_score(y_test,y_pred)
print("Accuracy:  ",resultdt*100,"%")
# print ('R Squared =',r2_score(y_test, y_pred))

Accuracy:   82.42954324586978 %

from sklearn import tree
tree.plot_tree(classifierDT.fit(x_train, y_train))

[Text(169.81144872864144, 216.09777777777776, 'X[1] <= -0.59\nentropy = 0.527\nsamples = 41158\nvalue = [36256, 4902]'),
 Text(63.40546476086937, 213.41333333333333, 'X[1] <= -1.103\nentropy = 0.417\nsamples = 19295\nvalue = [17671, 1624]'),
 Text(35.77936690756467, 210.7288888888889, 'X[0] <= 3.37\nentropy = 0.356\nsamples = 9798\nvalue = [9138, 660]'),
 Text(13.100012921163083, 208.04444444444445, 'X[0] <= -1.433\nentropy = 0.351\nsamples = 9734\nvalue = [9091, 643]'),
 Text(4.57796273358344, 205.35999999999999, 'X[0] <= -1.434\nentropy = 0.419\nsamples = 1802\nvalue = [1649, 153]'),
 Text(4.479412577192811, 202.67555555555555, 'X[0] <= -4.371\nentropy = 0.416\nsamples = 1800\nvalue = [1649, 151]'),
 Text(4.380862420802182, 199.9911111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(4.57796273358344, 199.9911111111111, 'X[1] <= -1.724\nentropy = 0.414\nsamples = 1799\nvalue = [1649, 150]'),
 Text(1.4536148067617785, 197.30666666666667, 'X[1] <= -1.75\nentropy = 0.551\nsamples = 196\nvalue = [171, 25]'),
 Text(0.9362264857109759, 194.6222222222222, 'X[1] <= -1.909\nentropy = 0.407\nsamples = 160\nvalue = [147, 13]'),
 Text(0.8376763293203469, 191.93777777777777, 'entropy = 0.0\nsamples = 26\nvalue = [26, 0]'),
 Text(1.034776642101605, 191.93777777777777, 'X[1] <= -1.908\nentropy = 0.459\nsamples = 134\nvalue = [121, 13]'),
 Text(0.9362264857109759, 189.25333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(1.133326798492234, 189.25333333333333, 'X[1] <= -1.768\nentropy = 0.437\nsamples = 133\nvalue = [121, 12]'),
 Text(1.034776642101605, 186.5688888888889, 'X[1] <= -1.769\nentropy = 0.485\nsamples = 114\nvalue = [102, 12]'),
 Text(0.9362264857109759, 183.88444444444445, 'X[1] <= -1.781\nentropy = 0.461\nsamples = 113\nvalue = [102, 11]'),
 Text(0.8376763293203469, 181.2, 'X[1] <= -1.783\nentropy = 0.51\nsamples = 97\nvalue = [86, 11]'),
 Text(0.7391261729297178, 178.51555555555555, 'X[0] <= -1.724\nentropy = 0.482\nsamples = 96\nvalue = [86, 10]'),
 Text(0.4927507819531452, 175.8311111111111, 'X[0] <= -2.094\nentropy = 0.294\nsamples = 58\nvalue = [55, 3]'),
 Text(0.39420062556251617, 173.14666666666668, 'X[0] <= -2.148\nentropy = 0.503\nsamples = 27\nvalue = [24, 3]'),
 Text(0.29565046917188714, 170.46222222222224, 'X[0] <= -2.602\nentropy = 0.391\nsamples = 26\nvalue = [24, 2]'),
 Text(0.19710031278125809, 167.77777777777777, 'X[0] <= -2.69\nentropy = 0.619\nsamples = 13\nvalue = [11, 2]'),
 Text(0.09855015639062904, 165.09333333333333, 'entropy = 0.0\nsamples = 9\nvalue = [9, 0]'),
 Text(0.29565046917188714, 165.09333333333333, 'X[1] <= -1.851\nentropy = 1.0\nsamples = 4\nvalue = [2, 2]'),
 Text(0.19710031278125809, 162.4088888888889, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(0.39420062556251617, 162.4088888888889, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.39420062556251617, 167.77777777777777, 'entropy = 0.0\nsamples = 13\nvalue = [13, 0]'),
 Text(0.4927507819531452, 170.46222222222224, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.5913009383437743, 173.14666666666668, 'entropy = 0.0\nsamples = 31\nvalue = [31, 0]'),
 Text(0.9855015639062904, 175.8311111111111, 'X[0] <= -1.66\nentropy = 0.689\nsamples = 38\nvalue = [31, 7]'),
 Text(0.7884012511250323, 173.14666666666668, 'X[0] <= -1.692\nentropy = 0.811\nsamples = 4\nvalue = [1, 3]'),
 Text(0.6898510947344033, 170.46222222222224, 'X[0] <= -1.705\nentropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(0.5913009383437743, 167.77777777777777, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.7884012511250323, 167.77777777777777, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.8869514075156614, 170.46222222222224, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(1.1826018766875486, 173.14666666666668, 'X[0] <= -1.608\nentropy = 0.523\nsamples = 34\nvalue = [30, 4]'),
 Text(1.0840517202969195, 170.46222222222224, 'entropy = 0.0\nsamples = 8\nvalue = [8, 0]'),
 Text(1.2811520330781776, 170.46222222222224, 'X[0] <= -1.605\nentropy = 0.619\nsamples = 26\nvalue = [22, 4]'),
 Text(1.1826018766875486, 167.77777777777777, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(1.3797021894688066, 167.77777777777777, 'X[0] <= -1.561\nentropy = 0.529\nsamples = 25\nvalue = [22, 3]'),
 Text(1.2811520330781776, 165.09333333333333, 'entropy = 0.0\nsamples = 6\nvalue = [6, 0]'),
 Text(1.4782523458594357, 165.09333333333333, 'X[0] <= -1.557\nentropy = 0.629\nsamples = 19\nvalue = [16, 3]'),
 Text(1.3797021894688066, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(1.5768025022500647, 162.4088888888889, 'X[0] <= -1.501\nentropy = 0.503\nsamples = 18\nvalue = [16, 2]'),
 Text(1.4782523458594357, 159.72444444444443, 'entropy = 0.0\nsamples = 8\nvalue = [8, 0]'),
 Text(1.6753526586406937, 159.72444444444443, 'X[0] <= -1.486\nentropy = 0.722\nsamples = 10\nvalue = [8, 2]'),
 Text(1.5768025022500647, 157.04, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(1.7739028150313227, 157.04, 'X[0] <= -1.46\nentropy = 0.503\nsamples = 9\nvalue = [8, 1]'),
 Text(1.6753526586406937, 154.35555555555555, 'entropy = 0.0\nsamples = 6\nvalue = [6, 0]'),
 Text(1.8724529714219518, 154.35555555555555, 'X[0] <= -1.456\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(1.7739028150313227, 151.67111111111112, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(1.9710031278125808, 151.67111111111112, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(0.9362264857109759, 178.51555555555555, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(1.034776642101605, 181.2, 'entropy = 0.0\nsamples = 16\nvalue = [16, 0]'),
 Text(1.133326798492234, 183.88444444444445, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(1.231876954882863, 186.5688888888889, 'entropy = 0.0\nsamples = 19\nvalue = [19, 0]'),
 Text(1.9710031278125808, 194.6222222222222, 'X[0] <= -1.996\nentropy = 0.918\nsamples = 36\nvalue = [24, 12]'),
 Text(1.7246277368360083, 191.93777777777777, 'X[0] <= -2.453\nentropy = 0.998\nsamples = 17\nvalue = [8, 9]'),
 Text(1.52752742405475, 189.25333333333333, 'X[1] <= -1.74\nentropy = 0.592\nsamples = 7\nvalue = [6, 1]'),
 Text(1.428977267664121, 186.5688888888889, 'X[0] <= -2.764\nentropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(1.330427111273492, 183.88444444444445, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(1.52752742405475, 183.88444444444445, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(1.6260775804453793, 186.5688888888889, 'entropy = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(1.9217280496172664, 189.25333333333333, 'X[1] <= -1.734\nentropy = 0.722\nsamples = 10\nvalue = [2, 8]'),
 Text(1.8231778932266374, 186.5688888888889, 'entropy = 0.0\nsamples = 7\nvalue = [0, 7]'),
 Text(2.0202782060078954, 186.5688888888889, 'X[1] <= -1.725\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(1.9217280496172664, 183.88444444444445, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(2.1188283623985242, 183.88444444444445, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(2.2173785187891535, 191.93777777777777, 'X[1] <= -1.74\nentropy = 0.629\nsamples = 19\nvalue = [16, 3]'),
 Text(2.1188283623985242, 189.25333333333333, 'entropy = 0.0\nsamples = 9\nvalue = [9, 0]'),
 Text(2.3159286751797823, 189.25333333333333, 'X[1] <= -1.738\nentropy = 0.881\nsamples = 10\nvalue = [7, 3]'),
 Text(2.2173785187891535, 186.5688888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(2.4144788315704115, 186.5688888888889, 'X[1] <= -1.725\nentropy = 0.764\nsamples = 9\nvalue = [7, 2]'),
 Text(2.3159286751797823, 183.88444444444445, 'X[0] <= -1.942\nentropy = 0.544\nsamples = 8\nvalue = [7, 1]'),
 Text(2.2173785187891535, 181.2, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(2.4144788315704115, 181.2, 'entropy = 0.0\nsamples = 6\nvalue = [6, 0]'),
 Text(2.513028987961041, 183.88444444444445, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(7.702310660405101, 197.30666666666667, 'X[1] <= -1.326\nentropy = 0.395\nsamples = 1603\nvalue = [1478, 125]'),
 Text(4.273073187249931, 194.6222222222222, 'X[0] <= -2.847\nentropy = 0.336\nsamples = 838\nvalue = [786, 52]'),
 Text(4.075972874468673, 191.93777777777777, 'X[0] <= -3.218\nentropy = 0.112\nsamples = 67\nvalue = [66, 1]'),
 Text(3.977422718078044, 189.25333333333333, 'X[0] <= -3.24\nentropy = 0.414\nsamples = 12\nvalue = [11, 1]'),
 Text(3.878872561687415, 186.5688888888889, 'entropy = 0.0\nsamples = 11\nvalue = [11, 0]'),
 Text(4.075972874468673, 186.5688888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(4.174523030859302, 189.25333333333333, 'entropy = 0.0\nsamples = 55\nvalue = [55, 0]'),
 Text(4.470173500031189, 191.93777777777777, 'X[0] <= -2.843\nentropy = 0.351\nsamples = 771\nvalue = [720, 51]'),
 Text(4.37162334364056, 189.25333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(4.5687236564218185, 189.25333333333333, 'X[1] <= -1.335\nentropy = 0.347\nsamples = 770\nvalue = [720, 50]'),
 Text(4.470173500031189, 186.5688888888889, 'X[1] <= -1.336\nentropy = 0.354\nsamples = 748\nvalue = [698, 50]'),
 Text(4.37162334364056, 183.88444444444445, 'X[1] <= -1.348\nentropy = 0.349\nsamples = 747\nvalue = [698, 49]'),
 Text(4.273073187249931, 181.2, 'X[1] <= -1.348\nentropy = 0.359\nsamples = 720\nvalue = [671, 49]'),
 Text(4.174523030859302, 178.51555555555555, 'X[1] <= -1.354\nentropy = 0.354\nsamples = 718\nvalue = [670, 48]'),
 Text(4.075972874468673, 175.8311111111111, 'X[1] <= -1.355\nentropy = 0.361\nsamples = 699\nvalue = [651, 48]'),
 Text(3.977422718078044, 173.14666666666668, 'X[1] <= -1.365\nentropy = 0.356\nsamples = 698\nvalue = [651, 47]'),
 Text(3.878872561687415, 170.46222222222224, 'X[1] <= -1.367\nentropy = 0.363\nsamples = 679\nvalue = [632, 47]'),
 Text(3.780322405296786, 167.77777777777777, 'X[1] <= -1.381\nentropy = 0.347\nsamples = 676\nvalue = [632, 44]'),
 Text(3.681772248906157, 165.09333333333333, 'X[1] <= -1.382\nentropy = 0.356\nsamples = 654\nvalue = [610, 44]'),
 Text(3.583222092515528, 162.4088888888889, 'X[1] <= -1.403\nentropy = 0.35\nsamples = 653\nvalue = [610, 43]'),
 Text(3.144365927338508, 159.72444444444443, 'X[1] <= -1.404\nentropy = 0.365\nsamples = 601\nvalue = [559, 42]'),
 Text(3.045815770947879, 157.04, 'X[1] <= -1.66\nentropy = 0.36\nsamples = 600\nvalue = [559, 41]'),
 Text(2.266653596984468, 154.35555555555555, 'X[1] <= -1.699\nentropy = 0.181\nsamples = 73\nvalue = [71, 2]'),
 Text(2.168103440593839, 151.67111111111112, 'X[1] <= -1.707\nentropy = 0.469\nsamples = 20\nvalue = [18, 2]'),
 Text(2.06955328420321, 148.98666666666668, 'entropy = 0.0\nsamples = 13\nvalue = [13, 0]'),
 Text(2.266653596984468, 148.98666666666668, 'X[0] <= -1.496\nentropy = 0.863\nsamples = 7\nvalue = [5, 2]'),
 Text(2.168103440593839, 146.3022222222222, 'X[1] <= -1.7\nentropy = 0.65\nsamples = 6\nvalue = [5, 1]'),
 Text(2.06955328420321, 143.61777777777777, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(2.266653596984468, 143.61777777777777, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(2.365203753375097, 146.3022222222222, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(2.365203753375097, 151.67111111111112, 'entropy = 0.0\nsamples = 53\nvalue = [53, 0]'),
 Text(3.8249779449112897, 154.35555555555555, 'X[1] <= -1.655\nentropy = 0.381\nsamples = 527\nvalue = [488, 39]'),
 Text(2.857954535328242, 151.67111111111112, 'X[0] <= -1.67\nentropy = 0.94\nsamples = 14\nvalue = [9, 5]'),
 Text(2.7594043789376133, 148.98666666666668, 'X[0] <= -1.851\nentropy = 1.0\nsamples = 10\nvalue = [5, 5]'),
 Text(2.562304066156355, 146.3022222222222, 'X[0] <= -2.166\nentropy = 0.918\nsamples = 6\nvalue = [4, 2]'),
 Text(2.463753909765726, 143.61777777777777, 'X[1] <= -1.657\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(2.365203753375097, 140.93333333333334, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(2.562304066156355, 140.93333333333334, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(2.660854222546984, 143.61777777777777, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(2.9565046917188713, 146.3022222222222, 'X[1] <= -1.657\nentropy = 0.811\nsamples = 4\nvalue = [1, 3]'),
 Text(2.857954535328242, 143.61777777777777, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(3.0550548481095, 143.61777777777777, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(2.9565046917188713, 148.98666666666668, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(4.792001354494337, 151.67111111111112, 'X[1] <= -1.527\nentropy = 0.352\nsamples = 513\nvalue = [479, 34]'),
 Text(3.5478056300626455, 148.98666666666668, 'X[0] <= -1.543\nentropy = 0.264\nsamples = 246\nvalue = [235, 11]'),
 Text(3.3507053172813874, 146.3022222222222, 'X[0] <= -1.956\nentropy = 0.187\nsamples = 210\nvalue = [204, 6]'),
 Text(3.2521551608907586, 143.61777777777777, 'X[0] <= -1.961\nentropy = 0.316\nsamples = 105\nvalue = [99, 6]'),
 Text(3.1536050045001294, 140.93333333333334, 'X[0] <= -2.2\nentropy = 0.278\nsamples = 104\nvalue = [99, 5]'),
 Text(3.0550548481095, 138.24888888888887, 'X[0] <= -2.243\nentropy = 0.414\nsamples = 60\nvalue = [55, 5]'),
 Text(2.857954535328242, 135.56444444444446, 'X[0] <= -2.526\nentropy = 0.232\nsamples = 53\nvalue = [51, 2]'),
 Text(2.7594043789376133, 132.88, 'X[0] <= -2.575\nentropy = 0.523\nsamples = 17\nvalue = [15, 2]'),
 Text(2.660854222546984, 130.19555555555556, 'entropy = 0.0\nsamples = 12\nvalue = [12, 0]'),
 Text(2.857954535328242, 130.19555555555556, 'X[1] <= -1.622\nentropy = 0.971\nsamples = 5\nvalue = [3, 2]'),
 Text(2.7594043789376133, 127.5111111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(2.9565046917188713, 127.5111111111111, 'X[0] <= -2.569\nentropy = 0.811\nsamples = 4\nvalue = [3, 1]'),
 Text(2.857954535328242, 124.82666666666667, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(3.0550548481095, 124.82666666666667, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(2.9565046917188713, 132.88, 'entropy = 0.0\nsamples = 36\nvalue = [36, 0]'),
 Text(3.2521551608907586, 135.56444444444446, 'X[0] <= -2.238\nentropy = 0.985\nsamples = 7\nvalue = [4, 3]'),
 Text(3.1536050045001294, 132.88, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(3.3507053172813874, 132.88, 'X[0] <= -2.202\nentropy = 0.918\nsamples = 6\nvalue = [4, 2]'),
 Text(3.2521551608907586, 130.19555555555556, 'X[1] <= -1.643\nentropy = 0.722\nsamples = 5\nvalue = [4, 1]'),
 Text(3.1536050045001294, 127.5111111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(3.3507053172813874, 127.5111111111111, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(3.4492554736720167, 130.19555555555556, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(3.2521551608907586, 138.24888888888887, 'entropy = 0.0\nsamples = 44\nvalue = [44, 0]'),
 Text(3.3507053172813874, 140.93333333333334, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(3.4492554736720167, 143.61777777777777, 'entropy = 0.0\nsamples = 105\nvalue = [105, 0]'),
 Text(3.7449059428439035, 146.3022222222222, 'X[0] <= -1.533\nentropy = 0.581\nsamples = 36\nvalue = [31, 5]'),
 Text(3.6463557864532747, 143.61777777777777, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(3.843456099234533, 143.61777777777777, 'X[1] <= -1.619\nentropy = 0.431\nsamples = 34\nvalue = [31, 3]'),
 Text(3.7449059428439035, 140.93333333333334, 'entropy = 0.0\nsamples = 12\nvalue = [12, 0]'),
 Text(3.9420062556251616, 140.93333333333334, 'X[1] <= -1.61\nentropy = 0.575\nsamples = 22\nvalue = [19, 3]'),
 Text(3.843456099234533, 138.24888888888887, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(4.040556412015791, 138.24888888888887, 'X[0] <= -1.485\nentropy = 0.454\nsamples = 21\nvalue = [19, 2]'),
 Text(3.9420062556251616, 135.56444444444446, 'X[0] <= -1.49\nentropy = 0.65\nsamples = 12\nvalue = [10, 2]'),
 Text(3.843456099234533, 132.88, 'X[1] <= -1.578\nentropy = 0.439\nsamples = 11\nvalue = [10, 1]'),
 Text(3.7449059428439035, 130.19555555555556, 'X[1] <= -1.584\nentropy = 0.811\nsamples = 4\nvalue = [3, 1]'),
 Text(3.6463557864532747, 127.5111111111111, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(3.843456099234533, 127.5111111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(3.9420062556251616, 130.19555555555556, 'entropy = 0.0\nsamples = 7\nvalue = [7, 0]'),
 Text(4.040556412015791, 132.88, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(4.13910656840642, 135.56444444444446, 'entropy = 0.0\nsamples = 9\nvalue = [9, 0]'),
 Text(6.036197078926029, 148.98666666666668, 'X[1] <= -1.527\nentropy = 0.423\nsamples = 267\nvalue = [244, 23]'),
 Text(5.9376469225354, 146.3022222222222, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(6.134747235316658, 146.3022222222222, 'X[0] <= -1.636\nentropy = 0.412\nsamples = 266\nvalue = [244, 22]'),
 Text(5.272433366898654, 143.61777777777777, 'X[0] <= -2.188\nentropy = 0.458\nsamples = 207\nvalue = [187, 20]'),
 Text(4.681132428554879, 140.93333333333334, 'X[0] <= -2.34\nentropy = 0.337\nsamples = 96\nvalue = [90, 6]'),
 Text(4.582582272164251, 138.24888888888887, 'X[0] <= -2.342\nentropy = 0.431\nsamples = 68\nvalue = [62, 6]'),
 Text(4.484032115773622, 135.56444444444446, 'X[1] <= -1.496\nentropy = 0.383\nsamples = 67\nvalue = [62, 5]'),
 Text(4.2376567247970485, 132.88, 'X[1] <= -1.496\nentropy = 0.722\nsamples = 15\nvalue = [12, 3]'),
 Text(4.13910656840642, 130.19555555555556, 'X[0] <= -2.716\nentropy = 0.592\nsamples = 14\nvalue = [12, 2]'),
 Text(4.040556412015791, 127.5111111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(4.2376567247970485, 127.5111111111111, 'X[1] <= -1.521\nentropy = 0.391\nsamples = 13\nvalue = [12, 1]'),
 Text(4.13910656840642, 124.82666666666667, 'X[0] <= -2.531\nentropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(4.040556412015791, 122.14222222222222, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(4.2376567247970485, 122.14222222222222, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(4.336206881187678, 124.82666666666667, 'entropy = 0.0\nsamples = 11\nvalue = [11, 0]'),
 Text(4.336206881187678, 130.19555555555556, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(4.730407506750194, 132.88, 'X[0] <= -2.799\nentropy = 0.235\nsamples = 52\nvalue = [50, 2]'),
 Text(4.533307193968936, 130.19555555555556, 'X[0] <= -2.811\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(4.434757037578307, 127.5111111111111, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(4.631857350359565, 127.5111111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(4.927507819531452, 130.19555555555556, 'X[0] <= -2.435\nentropy = 0.144\nsamples = 49\nvalue = [48, 1]'),
 Text(4.828957663140823, 127.5111111111111, 'entropy = 0.0\nsamples = 36\nvalue = [36, 0]'),
 Text(5.026057975922082, 127.5111111111111, 'X[0] <= -2.431\nentropy = 0.391\nsamples = 13\nvalue = [12, 1]'),
 Text(4.927507819531452, 124.82666666666667, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(5.12460813231271, 124.82666666666667, 'entropy = 0.0\nsamples = 12\nvalue = [12, 0]'),
 Text(4.681132428554879, 135.56444444444446, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(4.779682584945508, 138.24888888888887, 'entropy = 0.0\nsamples = 28\nvalue = [28, 0]'),
 Text(5.863734305242428, 140.93333333333334, 'X[0] <= -2.173\nentropy = 0.547\nsamples = 111\nvalue = [97, 14]'),
 Text(5.617358914265855, 138.24888888888887, 'X[1] <= -1.489\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(5.5188087578752265, 135.56444444444446, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(5.715909070656484, 135.56444444444446, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(6.110109696219, 138.24888888888887, 'X[1] <= -1.475\nentropy = 0.503\nsamples = 108\nvalue = [96, 12]'),
 Text(5.913009383437743, 135.56444444444446, 'X[1] <= -1.477\nentropy = 0.675\nsamples = 45\nvalue = [37, 8]'),
 Text(5.814459227047114, 132.88, 'X[0] <= -1.891\nentropy = 0.632\nsamples = 44\nvalue = [37, 7]'),
 Text(5.617358914265855, 130.19555555555556, 'X[0] <= -1.915\nentropy = 0.779\nsamples = 26\nvalue = [20, 6]'),
 Text(5.5188087578752265, 127.5111111111111, 'X[1] <= -1.523\nentropy = 0.722\nsamples = 25\nvalue = [20, 5]'),
 Text(5.321708445093968, 124.82666666666667, 'X[0] <= -1.984\nentropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(5.223158288703339, 122.14222222222222, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(5.420258601484598, 122.14222222222222, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(5.715909070656484, 124.82666666666667, 'X[1] <= -1.512\nentropy = 0.667\nsamples = 23\nvalue = [19, 4]'),
 Text(5.617358914265855, 122.14222222222222, 'entropy = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(5.814459227047114, 122.14222222222222, 'X[1] <= -1.51\nentropy = 0.764\nsamples = 18\nvalue = [14, 4]'),
 Text(5.715909070656484, 119.45777777777778, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(5.913009383437743, 119.45777777777778, 'X[0] <= -2.106\nentropy = 0.672\nsamples = 17\nvalue = [14, 3]'),
 Text(5.715909070656484, 116.77333333333333, 'X[0] <= -2.126\nentropy = 0.971\nsamples = 5\nvalue = [3, 2]'),
 Text(5.617358914265855, 114.08888888888889, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(5.814459227047114, 114.08888888888889, 'X[0] <= -2.116\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(5.715909070656484, 111.40444444444444, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(5.913009383437743, 111.40444444444444, 'X[0] <= -2.107\nentropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(5.814459227047114, 108.72, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(6.011559539828371, 108.72, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(6.110109696219, 116.77333333333333, 'X[1] <= -1.483\nentropy = 0.414\nsamples = 12\nvalue = [11, 1]'),
 Text(6.011559539828371, 114.08888888888889, 'entropy = 0.0\nsamples = 10\nvalue = [10, 0]'),
 Text(6.20865985260963, 114.08888888888889, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(5.715909070656484, 127.5111111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(6.011559539828371, 130.19555555555556, 'X[0] <= -1.639\nentropy = 0.31\nsamples = 18\nvalue = [17, 1]'),
 Text(5.913009383437743, 127.5111111111111, 'entropy = 0.0\nsamples = 15\nvalue = [15, 0]'),
 Text(6.110109696219, 127.5111111111111, 'entropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(6.011559539828371, 132.88, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(6.307210009000259, 135.56444444444446, 'X[1] <= -1.445\nentropy = 0.341\nsamples = 63\nvalue = [59, 4]'),
 Text(6.20865985260963, 132.88, 'entropy = 0.0\nsamples = 18\nvalue = [18, 0]'),
 Text(6.4057601653908876, 132.88, 'X[1] <= -1.444\nentropy = 0.433\nsamples = 45\nvalue = [41, 4]'),
 Text(6.307210009000259, 130.19555555555556, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(6.504310321781517, 130.19555555555556, 'X[1] <= -1.428\nentropy = 0.359\nsamples = 44\nvalue = [41, 3]'),
 Text(6.4057601653908876, 127.5111111111111, 'entropy = 0.0\nsamples = 16\nvalue = [16, 0]'),
 Text(6.602860478172146, 127.5111111111111, 'X[1] <= -1.423\nentropy = 0.491\nsamples = 28\nvalue = [25, 3]'),
 Text(6.4057601653908876, 124.82666666666667, 'X[1] <= -1.425\nentropy = 0.811\nsamples = 8\nvalue = [6, 2]'),
 Text(6.307210009000259, 122.14222222222222, 'X[1] <= -1.427\nentropy = 0.592\nsamples = 7\nvalue = [6, 1]'),
 Text(6.20865985260963, 119.45777777777778, 'entropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(6.4057601653908876, 119.45777777777778, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(6.504310321781517, 122.14222222222222, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(6.799960790953404, 124.82666666666667, 'X[0] <= -1.771\nentropy = 0.286\nsamples = 20\nvalue = [19, 1]'),
 Text(6.701410634562775, 122.14222222222222, 'entropy = 0.0\nsamples = 14\nvalue = [14, 0]'),
 Text(6.898510947344033, 122.14222222222222, 'X[0] <= -1.743\nentropy = 0.65\nsamples = 6\nvalue = [5, 1]'),
 Text(6.799960790953404, 119.45777777777778, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(6.997061103734662, 119.45777777777778, 'entropy = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(6.997061103734662, 143.61777777777777, 'X[1] <= -1.486\nentropy = 0.214\nsamples = 59\nvalue = [57, 2]'),
 Text(6.898510947344033, 140.93333333333334, 'X[1] <= -1.491\nentropy = 0.485\nsamples = 19\nvalue = [17, 2]'),
 Text(6.799960790953404, 138.24888888888887, 'X[1] <= -1.516\nentropy = 0.31\nsamples = 18\nvalue = [17, 1]'),
 Text(6.701410634562775, 135.56444444444446, 'X[1] <= -1.517\nentropy = 0.722\nsamples = 5\nvalue = [4, 1]'),
 Text(6.602860478172146, 132.88, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(6.799960790953404, 132.88, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(6.898510947344033, 135.56444444444446, 'entropy = 0.0\nsamples = 13\nvalue = [13, 0]'),
 Text(6.997061103734662, 138.24888888888887, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(7.095611260125291, 140.93333333333334, 'entropy = 0.0\nsamples = 40\nvalue = [40, 0]'),
 Text(3.242916083729137, 157.04, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(4.022078257692548, 159.72444444444443, 'X[0] <= -1.568\nentropy = 0.137\nsamples = 52\nvalue = [51, 1]'),
 Text(3.923528101301919, 157.04, 'entropy = 0.0\nsamples = 43\nvalue = [43, 0]'),
 Text(4.120628414083177, 157.04, 'X[0] <= -1.548\nentropy = 0.503\nsamples = 9\nvalue = [8, 1]'),
 Text(4.022078257692548, 154.35555555555555, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(4.219178570473806, 154.35555555555555, 'entropy = 0.0\nsamples = 8\nvalue = [8, 0]'),
 Text(3.780322405296786, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(3.878872561687415, 165.09333333333333, 'entropy = 0.0\nsamples = 22\nvalue = [22, 0]'),
 Text(3.977422718078044, 167.77777777777777, 'entropy = 0.0\nsamples = 3\nvalue = [0, 3]'),
 Text(4.075972874468673, 170.46222222222224, 'entropy = 0.0\nsamples = 19\nvalue = [19, 0]'),
 Text(4.174523030859302, 173.14666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(4.273073187249931, 175.8311111111111, 'entropy = 0.0\nsamples = 19\nvalue = [19, 0]'),
 Text(4.37162334364056, 178.51555555555555, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(4.470173500031189, 181.2, 'entropy = 0.0\nsamples = 27\nvalue = [27, 0]'),
 Text(4.5687236564218185, 183.88444444444445, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(4.667273812812447, 186.5688888888889, 'entropy = 0.0\nsamples = 22\nvalue = [22, 0]'),
 Text(11.13154813356027, 194.6222222222222, 'X[0] <= -1.478\nentropy = 0.454\nsamples = 765\nvalue = [692, 73]'),
 Text(9.32838824085048, 191.93777777777777, 'X[0] <= -1.514\nentropy = 0.436\nsamples = 735\nvalue = [669, 66]'),
 Text(9.229838084459852, 189.25333333333333, 'X[1] <= -1.326\nentropy = 0.449\nsamples = 704\nvalue = [638, 66]'),
 Text(9.131287928069222, 186.5688888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(9.32838824085048, 186.5688888888889, 'X[0] <= -1.514\nentropy = 0.445\nsamples = 703\nvalue = [638, 65]'),
 Text(9.229838084459852, 183.88444444444445, 'X[0] <= -1.845\nentropy = 0.44\nsamples = 702\nvalue = [638, 64]'),
 Text(7.600680811627265, 181.2, 'X[0] <= -2.821\nentropy = 0.393\nsamples = 478\nvalue = [441, 37]'),
 Text(6.824598330051061, 178.51555555555555, 'X[0] <= -2.83\nentropy = 0.588\nsamples = 92\nvalue = [79, 13]'),
 Text(6.726048173660432, 175.8311111111111, 'X[1] <= -1.126\nentropy = 0.563\nsamples = 91\nvalue = [79, 12]'),
 Text(6.6274980172698035, 173.14666666666668, 'X[1] <= -1.126\nentropy = 0.605\nsamples = 81\nvalue = [69, 12]'),
 Text(6.528947860879174, 170.46222222222224, 'X[1] <= -1.283\nentropy = 0.516\nsamples = 78\nvalue = [69, 9]'),
 Text(6.331847548097916, 167.77777777777777, 'X[1] <= -1.286\nentropy = 0.837\nsamples = 15\nvalue = [11, 4]'),
 Text(6.233297391707287, 165.09333333333333, 'X[0] <= -2.97\nentropy = 0.75\nsamples = 14\nvalue = [11, 3]'),
 Text(6.134747235316658, 162.4088888888889, 'X[0] <= -3.009\nentropy = 0.845\nsamples = 11\nvalue = [8, 3]'),
 Text(5.9376469225354, 159.72444444444443, 'X[1] <= -1.292\nentropy = 0.544\nsamples = 8\nvalue = [7, 1]'),
 Text(5.83909676614477, 157.04, 'entropy = 0.0\nsamples = 6\nvalue = [6, 0]'),
 Text(6.036197078926029, 157.04, 'X[0] <= -3.301\nentropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(5.9376469225354, 154.35555555555555, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(6.134747235316658, 154.35555555555555, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(6.331847548097916, 159.72444444444443, 'X[0] <= -2.974\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(6.233297391707287, 157.04, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(6.430397704488545, 157.04, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(6.331847548097916, 162.4088888888889, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(6.430397704488545, 165.09333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(6.726048173660432, 167.77777777777777, 'X[1] <= -1.211\nentropy = 0.4\nsamples = 63\nvalue = [58, 5]'),
 Text(6.6274980172698035, 165.09333333333333, 'entropy = 0.0\nsamples = 29\nvalue = [29, 0]'),
 Text(6.824598330051061, 165.09333333333333, 'X[1] <= -1.209\nentropy = 0.602\nsamples = 34\nvalue = [29, 5]'),
 Text(6.726048173660432, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(6.92314848644169, 162.4088888888889, 'X[0] <= -3.04\nentropy = 0.533\nsamples = 33\nvalue = [29, 4]'),
 Text(6.824598330051061, 159.72444444444443, 'X[0] <= -3.057\nentropy = 0.702\nsamples = 21\nvalue = [17, 4]'),
 Text(6.726048173660432, 157.04, 'X[1] <= -1.14\nentropy = 0.485\nsamples = 19\nvalue = [17, 2]'),
 Text(6.6274980172698035, 154.35555555555555, 'X[1] <= -1.149\nentropy = 0.592\nsamples = 14\nvalue = [12, 2]'),
 Text(6.528947860879174, 151.67111111111112, 'X[0] <= -3.786\nentropy = 0.391\nsamples = 13\nvalue = [12, 1]'),
 Text(6.430397704488545, 148.98666666666668, 'X[1] <= -1.187\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(6.331847548097916, 146.3022222222222, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(6.528947860879174, 146.3022222222222, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(6.6274980172698035, 148.98666666666668, 'entropy = 0.0\nsamples = 10\nvalue = [10, 0]'),
 Text(6.726048173660432, 151.67111111111112, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(6.824598330051061, 154.35555555555555, 'entropy = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(6.92314848644169, 157.04, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(7.02169864283232, 159.72444444444443, 'entropy = 0.0\nsamples = 12\nvalue = [12, 0]'),
 Text(6.726048173660432, 170.46222222222224, 'entropy = 0.0\nsamples = 3\nvalue = [0, 3]'),
 Text(6.824598330051061, 173.14666666666668, 'entropy = 0.0\nsamples = 10\nvalue = [10, 0]'),
 Text(6.92314848644169, 175.8311111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(8.376763293203469, 178.51555555555555, 'X[0] <= -1.882\nentropy = 0.336\nsamples = 386\nvalue = [362, 24]'),
 Text(8.27821313681284, 175.8311111111111, 'X[0] <= -1.885\nentropy = 0.357\nsamples = 355\nvalue = [331, 24]'),
 Text(8.179662980422211, 173.14666666666668, 'X[1] <= -1.117\nentropy = 0.347\nsamples = 354\nvalue = [331, 23]'),
 Text(7.711549737566723, 170.46222222222224, 'X[1] <= -1.139\nentropy = 0.31\nsamples = 324\nvalue = [306, 18]'),
 Text(7.612999581176093, 167.77777777777777, 'X[1] <= -1.141\nentropy = 0.335\nsamples = 291\nvalue = [273, 18]'),
 Text(7.5144494247854645, 165.09333333333333, 'X[1] <= -1.323\nentropy = 0.309\nsamples = 289\nvalue = [273, 16]'),
 Text(7.317349112004206, 162.4088888888889, 'X[0] <= -2.511\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(7.218798955613577, 159.72444444444443, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(7.415899268394836, 159.72444444444443, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(7.711549737566723, 162.4088888888889, 'X[1] <= -1.301\nentropy = 0.297\nsamples = 286\nvalue = [271, 15]'),
 Text(7.612999581176093, 159.72444444444443, 'entropy = 0.0\nsamples = 35\nvalue = [35, 0]'),
 Text(7.810099893957352, 159.72444444444443, 'X[1] <= -1.3\nentropy = 0.326\nsamples = 251\nvalue = [236, 15]'),
 Text(7.711549737566723, 157.04, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(7.908650050347981, 157.04, 'X[0] <= -2.722\nentropy = 0.311\nsamples = 250\nvalue = [236, 14]'),
 Text(7.810099893957352, 154.35555555555555, 'entropy = 0.0\nsamples = 15\nvalue = [15, 0]'),
 Text(8.00720020673861, 154.35555555555555, 'X[0] <= -2.694\nentropy = 0.326\nsamples = 235\nvalue = [221, 14]'),
 Text(7.810099893957352, 151.67111111111112, 'X[1] <= -1.197\nentropy = 0.971\nsamples = 5\nvalue = [3, 2]'),
 Text(7.711549737566723, 148.98666666666668, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(7.908650050347981, 148.98666666666668, 'X[1] <= -1.177\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(7.810099893957352, 146.3022222222222, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(8.00720020673861, 146.3022222222222, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(8.204300519519867, 151.67111111111112, 'X[0] <= -2.562\nentropy = 0.296\nsamples = 230\nvalue = [218, 12]'),
 Text(8.10575036312924, 148.98666666666668, 'entropy = 0.0\nsamples = 25\nvalue = [25, 0]'),
 Text(8.302850675910497, 148.98666666666668, 'X[0] <= -2.56\nentropy = 0.322\nsamples = 205\nvalue = [193, 12]'),
 Text(8.204300519519867, 146.3022222222222, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(8.401400832301126, 146.3022222222222, 'X[0] <= -2.42\nentropy = 0.303\nsamples = 204\nvalue = [193, 11]'),
 Text(8.302850675910497, 143.61777777777777, 'entropy = 0.0\nsamples = 35\nvalue = [35, 0]'),
 Text(8.499950988691754, 143.61777777777777, 'X[0] <= -2.414\nentropy = 0.347\nsamples = 169\nvalue = [158, 11]'),
 Text(8.302850675910497, 140.93333333333334, 'X[1] <= -1.215\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(8.204300519519867, 138.24888888888887, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(8.401400832301126, 138.24888888888887, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(8.697051301473014, 140.93333333333334, 'X[1] <= -1.263\nentropy = 0.304\nsamples = 166\nvalue = [157, 9]'),
 Text(8.598501145082384, 138.24888888888887, 'entropy = 0.0\nsamples = 40\nvalue = [40, 0]'),
 Text(8.795601457863642, 138.24888888888887, 'X[1] <= -1.262\nentropy = 0.371\nsamples = 126\nvalue = [117, 9]'),
 Text(8.697051301473014, 135.56444444444446, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(8.894151614254271, 135.56444444444446, 'X[1] <= -1.255\nentropy = 0.343\nsamples = 125\nvalue = [117, 8]'),
 Text(8.795601457863642, 132.88, 'entropy = 0.0\nsamples = 11\nvalue = [11, 0]'),
 Text(8.9927017706449, 132.88, 'X[1] <= -1.254\nentropy = 0.367\nsamples = 114\nvalue = [106, 8]'),
 Text(8.894151614254271, 130.19555555555556, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(9.091251927035529, 130.19555555555556, 'X[1] <= -1.229\nentropy = 0.335\nsamples = 113\nvalue = [106, 7]'),
 Text(8.9927017706449, 127.5111111111111, 'entropy = 0.0\nsamples = 23\nvalue = [23, 0]'),
 Text(9.189802083426159, 127.5111111111111, 'X[1] <= -1.224\nentropy = 0.394\nsamples = 90\nvalue = [83, 7]'),
 Text(8.943426692449586, 124.82666666666667, 'X[0] <= -2.202\nentropy = 1.0\nsamples = 4\nvalue = [2, 2]'),
 Text(8.844876536058957, 122.14222222222222, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(9.041976848840214, 122.14222222222222, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(9.436177474402731, 124.82666666666667, 'X[0] <= -2.367\nentropy = 0.32\nsamples = 86\nvalue = [81, 5]'),
 Text(9.239077161621474, 122.14222222222222, 'X[0] <= -2.38\nentropy = 0.811\nsamples = 4\nvalue = [3, 1]'),
 Text(9.140527005230844, 119.45777777777778, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(9.337627318012101, 119.45777777777778, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(9.633277787183989, 122.14222222222222, 'X[0] <= -2.234\nentropy = 0.281\nsamples = 82\nvalue = [78, 4]'),
 Text(9.534727630793359, 119.45777777777778, 'entropy = 0.0\nsamples = 13\nvalue = [13, 0]'),
 Text(9.731827943574618, 119.45777777777778, 'X[0] <= -2.219\nentropy = 0.319\nsamples = 69\nvalue = [65, 4]'),
 Text(9.633277787183989, 116.77333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(9.830378099965246, 116.77333333333333, 'X[1] <= -1.152\nentropy = 0.261\nsamples = 68\nvalue = [65, 3]'),
 Text(9.633277787183989, 114.08888888888889, 'X[1] <= -1.169\nentropy = 0.203\nsamples = 63\nvalue = [61, 2]'),
 Text(9.534727630793359, 111.40444444444444, 'X[1] <= -1.17\nentropy = 0.267\nsamples = 44\nvalue = [42, 2]'),
 Text(9.436177474402731, 108.72, 'X[1] <= -1.211\nentropy = 0.159\nsamples = 43\nvalue = [42, 1]'),
 Text(9.337627318012101, 106.03555555555556, 'X[1] <= -1.212\nentropy = 0.439\nsamples = 11\nvalue = [10, 1]'),
 Text(9.239077161621474, 103.35111111111111, 'entropy = 0.0\nsamples = 9\nvalue = [9, 0]'),
 Text(9.436177474402731, 103.35111111111111, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(9.534727630793359, 106.03555555555556, 'entropy = 0.0\nsamples = 32\nvalue = [32, 0]'),
 Text(9.633277787183989, 108.72, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(9.731827943574618, 111.40444444444444, 'entropy = 0.0\nsamples = 19\nvalue = [19, 0]'),
 Text(10.027478412746506, 114.08888888888889, 'X[1] <= -1.148\nentropy = 0.722\nsamples = 5\nvalue = [4, 1]'),
 Text(9.928928256355876, 111.40444444444444, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(10.126028569137134, 111.40444444444444, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(7.711549737566723, 165.09333333333333, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(7.810099893957352, 167.77777777777777, 'entropy = 0.0\nsamples = 33\nvalue = [33, 0]'),
 Text(8.647776223277699, 170.46222222222224, 'X[1] <= -1.11\nentropy = 0.65\nsamples = 30\nvalue = [25, 5]'),
 Text(8.401400832301126, 167.77777777777777, 'X[0] <= -2.247\nentropy = 0.946\nsamples = 11\nvalue = [7, 4]'),
 Text(8.204300519519867, 165.09333333333333, 'X[1] <= -1.113\nentropy = 0.971\nsamples = 5\nvalue = [2, 3]'),
 Text(8.10575036312924, 162.4088888888889, 'X[1] <= -1.115\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(8.00720020673861, 159.72444444444443, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(8.204300519519867, 159.72444444444443, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(8.302850675910497, 162.4088888888889, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(8.598501145082384, 165.09333333333333, 'X[1] <= -1.117\nentropy = 0.65\nsamples = 6\nvalue = [5, 1]'),
 Text(8.499950988691754, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(8.697051301473014, 162.4088888888889, 'entropy = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(8.894151614254271, 167.77777777777777, 'X[1] <= -1.106\nentropy = 0.297\nsamples = 19\nvalue = [18, 1]'),
 Text(8.795601457863642, 165.09333333333333, 'entropy = 0.0\nsamples = 14\nvalue = [14, 0]'),
 Text(8.9927017706449, 165.09333333333333, 'X[1] <= -1.105\nentropy = 0.722\nsamples = 5\nvalue = [4, 1]'),
 Text(8.894151614254271, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(9.091251927035529, 162.4088888888889, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(8.376763293203469, 173.14666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(8.475313449594097, 175.8311111111111, 'entropy = 0.0\nsamples = 31\nvalue = [31, 0]'),
 Text(10.858995357292438, 181.2, 'X[1] <= -1.2\nentropy = 0.531\nsamples = 224\nvalue = [197, 27]'),
 Text(9.768784252221105, 178.51555555555555, 'X[0] <= -1.827\nentropy = 0.673\nsamples = 130\nvalue = [107, 23]'),
 Text(9.288352239816787, 175.8311111111111, 'X[0] <= -1.83\nentropy = 0.918\nsamples = 6\nvalue = [2, 4]'),
 Text(9.189802083426159, 173.14666666666668, 'X[0] <= -1.838\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(9.091251927035529, 170.46222222222224, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(9.288352239816787, 170.46222222222224, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(9.386902396207416, 173.14666666666668, 'entropy = 0.0\nsamples = 3\nvalue = [0, 3]'),
 Text(10.24921626462542, 175.8311111111111, 'X[0] <= -1.727\nentropy = 0.618\nsamples = 124\nvalue = [105, 19]'),
 Text(9.584002708988674, 173.14666666666668, 'X[1] <= -1.299\nentropy = 0.794\nsamples = 46\nvalue = [35, 11]'),
 Text(9.485452552598046, 170.46222222222224, 'entropy = 0.0\nsamples = 10\nvalue = [10, 0]'),
 Text(9.682552865379304, 170.46222222222224, 'X[0] <= -1.8\nentropy = 0.888\nsamples = 36\nvalue = [25, 11]'),
 Text(9.485452552598046, 167.77777777777777, 'X[0] <= -1.813\nentropy = 0.469\nsamples = 10\nvalue = [9, 1]'),
 Text(9.386902396207416, 165.09333333333333, 'X[0] <= -1.818\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(9.288352239816787, 162.4088888888889, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(9.485452552598046, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(9.584002708988674, 165.09333333333333, 'entropy = 0.0\nsamples = 7\nvalue = [7, 0]'),
 Text(9.879653178160561, 167.77777777777777, 'X[0] <= -1.797\nentropy = 0.961\nsamples = 26\nvalue = [16, 10]'),
 Text(9.781103021769933, 165.09333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(9.978203334551191, 165.09333333333333, 'X[1] <= -1.298\nentropy = 0.943\nsamples = 25\nvalue = [16, 9]'),
 Text(9.879653178160561, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(10.076753490941819, 162.4088888888889, 'X[1] <= -1.287\nentropy = 0.918\nsamples = 24\nvalue = [16, 8]'),
 Text(9.978203334551191, 159.72444444444443, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(10.175303647332449, 159.72444444444443, 'X[0] <= -1.763\nentropy = 0.959\nsamples = 21\nvalue = [13, 8]'),
 Text(9.978203334551191, 157.04, 'X[1] <= -1.246\nentropy = 0.991\nsamples = 9\nvalue = [4, 5]'),
 Text(9.879653178160561, 154.35555555555555, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(10.076753490941819, 154.35555555555555, 'X[0] <= -1.791\nentropy = 1.0\nsamples = 8\nvalue = [4, 4]'),
 Text(9.978203334551191, 151.67111111111112, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(10.175303647332449, 151.67111111111112, 'X[0] <= -1.785\nentropy = 0.985\nsamples = 7\nvalue = [4, 3]'),
 Text(10.076753490941819, 148.98666666666668, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(10.273853803723078, 148.98666666666668, 'X[1] <= -1.238\nentropy = 0.971\nsamples = 5\nvalue = [2, 3]'),
 Text(10.175303647332449, 146.3022222222222, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(10.372403960113706, 146.3022222222222, 'X[0] <= -1.773\nentropy = 1.0\nsamples = 4\nvalue = [2, 2]'),
 Text(10.273853803723078, 143.61777777777777, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(10.470954116504336, 143.61777777777777, 'X[1] <= -1.219\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(10.372403960113706, 140.93333333333334, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(10.569504272894966, 140.93333333333334, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(10.372403960113706, 157.04, 'X[0] <= -1.739\nentropy = 0.811\nsamples = 12\nvalue = [9, 3]'),
 Text(10.273853803723078, 154.35555555555555, 'entropy = 0.0\nsamples = 7\nvalue = [7, 0]'),
 Text(10.470954116504336, 154.35555555555555, 'X[1] <= -1.236\nentropy = 0.971\nsamples = 5\nvalue = [2, 3]'),
 Text(10.372403960113706, 151.67111111111112, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(10.569504272894966, 151.67111111111112, 'X[0] <= -1.734\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(10.470954116504336, 148.98666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(10.668054429285593, 148.98666666666668, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(10.914429820262166, 173.14666666666668, 'X[1] <= -1.29\nentropy = 0.477\nsamples = 78\nvalue = [70, 8]'),
 Text(10.668054429285593, 170.46222222222224, 'X[1] <= -1.292\nentropy = 0.764\nsamples = 27\nvalue = [21, 6]'),
 Text(10.569504272894966, 167.77777777777777, 'X[1] <= -1.301\nentropy = 0.634\nsamples = 25\nvalue = [21, 4]'),
 Text(10.470954116504336, 165.09333333333333, 'X[0] <= -1.685\nentropy = 0.787\nsamples = 17\nvalue = [13, 4]'),
 Text(10.372403960113706, 162.4088888888889, 'entropy = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(10.569504272894966, 162.4088888888889, 'X[1] <= -1.323\nentropy = 0.918\nsamples = 12\nvalue = [8, 4]'),
 Text(10.470954116504336, 159.72444444444443, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(10.668054429285593, 159.72444444444443, 'X[1] <= -1.32\nentropy = 0.946\nsamples = 11\nvalue = [7, 4]'),
 Text(10.569504272894966, 157.04, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(10.766604585676223, 157.04, 'X[1] <= -1.307\nentropy = 0.881\nsamples = 10\nvalue = [7, 3]'),
 Text(10.668054429285593, 154.35555555555555, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(10.865154742066853, 154.35555555555555, 'X[1] <= -1.304\nentropy = 0.985\nsamples = 7\nvalue = [4, 3]'),
 Text(10.766604585676223, 151.67111111111112, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(10.96370489845748, 151.67111111111112, 'X[1] <= -1.302\nentropy = 0.722\nsamples = 5\nvalue = [4, 1]'),
 Text(10.865154742066853, 148.98666666666668, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(11.06225505484811, 148.98666666666668, 'entropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(10.668054429285593, 165.09333333333333, 'entropy = 0.0\nsamples = 8\nvalue = [8, 0]'),
 Text(10.766604585676223, 167.77777777777777, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(11.160805211238738, 170.46222222222224, 'X[0] <= -1.709\nentropy = 0.239\nsamples = 51\nvalue = [49, 2]'),
 Text(10.96370489845748, 167.77777777777777, 'X[0] <= -1.715\nentropy = 0.811\nsamples = 4\nvalue = [3, 1]'),
 Text(10.865154742066853, 165.09333333333333, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(11.06225505484811, 165.09333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(11.357905524019998, 167.77777777777777, 'X[1] <= -1.218\nentropy = 0.149\nsamples = 47\nvalue = [46, 1]'),
 Text(11.259355367629368, 165.09333333333333, 'entropy = 0.0\nsamples = 40\nvalue = [40, 0]'),
 Text(11.456455680410626, 165.09333333333333, 'X[1] <= -1.218\nentropy = 0.592\nsamples = 7\nvalue = [6, 1]'),
 Text(11.357905524019998, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(11.555005836801255, 162.4088888888889, 'entropy = 0.0\nsamples = 6\nvalue = [6, 0]'),
 Text(11.94920646236377, 178.51555555555555, 'X[0] <= -1.733\nentropy = 0.254\nsamples = 94\nvalue = [90, 4]'),
 Text(11.850656305973143, 175.8311111111111, 'entropy = 0.0\nsamples = 28\nvalue = [28, 0]'),
 Text(12.0477566187544, 175.8311111111111, 'X[0] <= -1.717\nentropy = 0.33\nsamples = 66\nvalue = [62, 4]'),
 Text(11.94920646236377, 173.14666666666668, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(12.14630677514503, 173.14666666666668, 'X[1] <= -1.143\nentropy = 0.201\nsamples = 64\nvalue = [62, 2]'),
 Text(12.0477566187544, 170.46222222222224, 'X[1] <= -1.144\nentropy = 0.303\nsamples = 37\nvalue = [35, 2]'),
 Text(11.94920646236377, 167.77777777777777, 'X[0] <= -1.677\nentropy = 0.183\nsamples = 36\nvalue = [35, 1]'),
 Text(11.850656305973143, 165.09333333333333, 'X[0] <= -1.678\nentropy = 0.503\nsamples = 9\nvalue = [8, 1]'),
 Text(11.752106149582513, 162.4088888888889, 'entropy = 0.0\nsamples = 8\nvalue = [8, 0]'),
 Text(11.94920646236377, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(12.0477566187544, 165.09333333333333, 'entropy = 0.0\nsamples = 27\nvalue = [27, 0]'),
 Text(12.14630677514503, 167.77777777777777, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(12.244856931535658, 170.46222222222224, 'entropy = 0.0\nsamples = 27\nvalue = [27, 0]'),
 Text(9.42693839724111, 183.88444444444445, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(9.42693839724111, 189.25333333333333, 'entropy = 0.0\nsamples = 31\nvalue = [31, 0]'),
 Text(12.934708026270062, 191.93777777777777, 'X[1] <= -1.151\nentropy = 0.784\nsamples = 30\nvalue = [23, 7]'),
 Text(12.836157869879433, 189.25333333333333, 'X[0] <= -1.473\nentropy = 0.871\nsamples = 24\nvalue = [17, 7]'),
 Text(12.737607713488805, 186.5688888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(12.934708026270062, 186.5688888888889, 'X[1] <= -1.153\nentropy = 0.828\nsamples = 23\nvalue = [17, 6]'),
 Text(12.836157869879433, 183.88444444444445, 'X[1] <= -1.195\nentropy = 0.773\nsamples = 22\nvalue = [17, 5]'),
 Text(12.737607713488805, 181.2, 'X[1] <= -1.199\nentropy = 0.896\nsamples = 16\nvalue = [11, 5]'),
 Text(12.639057557098175, 178.51555555555555, 'X[1] <= -1.258\nentropy = 0.837\nsamples = 15\nvalue = [11, 4]'),
 Text(12.441957244316917, 175.8311111111111, 'X[0] <= -1.468\nentropy = 1.0\nsamples = 6\nvalue = [3, 3]'),
 Text(12.343407087926288, 173.14666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(12.540507400707545, 173.14666666666668, 'X[0] <= -1.443\nentropy = 0.971\nsamples = 5\nvalue = [2, 3]'),
 Text(12.441957244316917, 170.46222222222224, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(12.639057557098175, 170.46222222222224, 'entropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(12.836157869879433, 175.8311111111111, 'X[1] <= -1.213\nentropy = 0.503\nsamples = 9\nvalue = [8, 1]'),
 Text(12.737607713488805, 173.14666666666668, 'entropy = 0.0\nsamples = 7\nvalue = [7, 0]'),
 Text(12.934708026270062, 173.14666666666668, 'X[0] <= -1.448\nentropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(12.836157869879433, 170.46222222222224, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(13.03325818266069, 170.46222222222224, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(12.836157869879433, 178.51555555555555, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(12.934708026270062, 181.2, 'entropy = 0.0\nsamples = 6\nvalue = [6, 0]'),
 Text(13.03325818266069, 183.88444444444445, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(13.03325818266069, 189.25333333333333, 'entropy = 0.0\nsamples = 6\nvalue = [6, 0]'),
 Text(4.676512889974068, 202.67555555555555, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(21.622063108742726, 205.35999999999999, 'X[1] <= -1.766\nentropy = 0.334\nsamples = 7932\nvalue = [7442, 490]'),
 Text(14.339047754836526, 202.67555555555555, 'X[0] <= 0.079\nentropy = 0.198\nsamples = 584\nvalue = [566, 18]'),
 Text(14.240497598445897, 199.9911111111111, 'X[0] <= 0.069\nentropy = 0.26\nsamples = 410\nvalue = [392, 18]'),
 Text(14.04339728566464, 197.30666666666667, 'X[1] <= -1.78\nentropy = 0.239\nsamples = 407\nvalue = [391, 16]'),
 Text(13.94484712927401, 194.6222222222222, 'X[1] <= -1.78\nentropy = 0.268\nsamples = 350\nvalue = [334, 16]'),
 Text(13.84629697288338, 191.93777777777777, 'X[1] <= -1.917\nentropy = 0.256\nsamples = 349\nvalue = [334, 15]'),
 Text(13.747746816492752, 189.25333333333333, 'entropy = 0.0\nsamples = 33\nvalue = [33, 0]'),
 Text(13.94484712927401, 189.25333333333333, 'X[1] <= -1.916\nentropy = 0.276\nsamples = 316\nvalue = [301, 15]'),
 Text(13.84629697288338, 186.5688888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(14.04339728566464, 186.5688888888889, 'X[0] <= -0.794\nentropy = 0.262\nsamples = 315\nvalue = [301, 14]'),
 Text(13.526008964613837, 183.88444444444445, 'X[0] <= -0.869\nentropy = 0.382\nsamples = 121\nvalue = [112, 9]'),
 Text(13.328908651832577, 181.2, 'X[0] <= -1.277\nentropy = 0.297\nsamples = 114\nvalue = [108, 6]'),
 Text(13.23035849544195, 178.51555555555555, 'entropy = 0.0\nsamples = 28\nvalue = [28, 0]'),
 Text(13.427458808223207, 178.51555555555555, 'X[0] <= -1.276\nentropy = 0.365\nsamples = 86\nvalue = [80, 6]'),
 Text(13.328908651832577, 175.8311111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(13.526008964613837, 175.8311111111111, 'X[0] <= -0.997\nentropy = 0.323\nsamples = 85\nvalue = [80, 5]'),
 Text(13.427458808223207, 173.14666666666668, 'X[0] <= -1.026\nentropy = 0.424\nsamples = 58\nvalue = [53, 5]'),
 Text(13.23035849544195, 170.46222222222224, 'X[1] <= -1.836\nentropy = 0.246\nsamples = 49\nvalue = [47, 2]'),
 Text(13.13180833905132, 167.77777777777777, 'X[1] <= -1.84\nentropy = 0.402\nsamples = 25\nvalue = [23, 2]'),
 Text(13.03325818266069, 165.09333333333333, 'X[1] <= -1.873\nentropy = 0.25\nsamples = 24\nvalue = [23, 1]'),
 Text(12.934708026270062, 162.4088888888889, 'X[1] <= -1.88\nentropy = 0.469\nsamples = 10\nvalue = [9, 1]'),
 Text(12.836157869879433, 159.72444444444443, 'entropy = 0.0\nsamples = 8\nvalue = [8, 0]'),
 Text(13.03325818266069, 159.72444444444443, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(13.13180833905132, 162.4088888888889, 'entropy = 0.0\nsamples = 14\nvalue = [14, 0]'),
 Text(13.23035849544195, 165.09333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(13.328908651832577, 167.77777777777777, 'entropy = 0.0\nsamples = 24\nvalue = [24, 0]'),
 Text(13.624559121004465, 170.46222222222224, 'X[0] <= -1.007\nentropy = 0.918\nsamples = 9\nvalue = [6, 3]'),
 Text(13.526008964613837, 167.77777777777777, 'X[0] <= -1.023\nentropy = 0.811\nsamples = 8\nvalue = [6, 2]'),
 Text(13.427458808223207, 165.09333333333333, 'X[0] <= -1.025\nentropy = 1.0\nsamples = 4\nvalue = [2, 2]'),
 Text(13.328908651832577, 162.4088888888889, 'entropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(13.526008964613837, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(13.624559121004465, 165.09333333333333, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(13.723109277395094, 167.77777777777777, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(13.624559121004465, 173.14666666666668, 'entropy = 0.0\nsamples = 27\nvalue = [27, 0]'),
 Text(13.723109277395094, 181.2, 'X[0] <= -0.843\nentropy = 0.985\nsamples = 7\nvalue = [4, 3]'),
 Text(13.624559121004465, 178.51555555555555, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(13.821659433785724, 178.51555555555555, 'X[0] <= -0.802\nentropy = 0.722\nsamples = 5\nvalue = [4, 1]'),
 Text(13.723109277395094, 175.8311111111111, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(13.920209590176352, 175.8311111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(14.560785606715442, 183.88444444444445, 'X[1] <= -1.804\nentropy = 0.173\nsamples = 194\nvalue = [189, 5]'),
 Text(14.462235450324812, 181.2, 'X[1] <= -1.804\nentropy = 0.234\nsamples = 131\nvalue = [126, 5]'),
 Text(14.363685293934182, 178.51555555555555, 'X[0] <= -0.162\nentropy = 0.198\nsamples = 130\nvalue = [126, 4]'),
 Text(14.11730990295761, 175.8311111111111, 'X[1] <= -1.82\nentropy = 0.092\nsamples = 85\nvalue = [84, 1]'),
 Text(14.018759746566982, 173.14666666666668, 'entropy = 0.0\nsamples = 66\nvalue = [66, 0]'),
 Text(14.21586005934824, 173.14666666666668, 'X[1] <= -1.818\nentropy = 0.297\nsamples = 19\nvalue = [18, 1]'),
 Text(14.11730990295761, 170.46222222222224, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(14.314410215738869, 170.46222222222224, 'entropy = 0.0\nsamples = 18\nvalue = [18, 0]'),
 Text(14.610060684910756, 175.8311111111111, 'X[0] <= -0.158\nentropy = 0.353\nsamples = 45\nvalue = [42, 3]'),
 Text(14.511510528520127, 173.14666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(14.708610841301384, 173.14666666666668, 'X[0] <= -0.121\nentropy = 0.267\nsamples = 44\nvalue = [42, 2]'),
 Text(14.511510528520127, 170.46222222222224, 'X[0] <= -0.128\nentropy = 0.722\nsamples = 5\nvalue = [4, 1]'),
 Text(14.412960372129497, 167.77777777777777, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(14.610060684910756, 167.77777777777777, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(14.905711154082642, 170.46222222222224, 'X[1] <= -1.815\nentropy = 0.172\nsamples = 39\nvalue = [38, 1]'),
 Text(14.807160997692014, 167.77777777777777, 'entropy = 0.0\nsamples = 31\nvalue = [31, 0]'),
 Text(15.004261310473272, 167.77777777777777, 'X[1] <= -1.814\nentropy = 0.544\nsamples = 8\nvalue = [7, 1]'),
 Text(14.905711154082642, 165.09333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(15.102811466863901, 165.09333333333333, 'entropy = 0.0\nsamples = 7\nvalue = [7, 0]'),
 Text(14.560785606715442, 178.51555555555555, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(14.65933576310607, 181.2, 'entropy = 0.0\nsamples = 63\nvalue = [63, 0]'),
 Text(14.04339728566464, 191.93777777777777, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(14.141947442055267, 194.6222222222222, 'entropy = 0.0\nsamples = 57\nvalue = [57, 0]'),
 Text(14.437597911227154, 197.30666666666667, 'X[0] <= 0.074\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(14.339047754836526, 194.6222222222222, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(14.536148067617784, 194.6222222222222, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(14.437597911227154, 199.9911111111111, 'entropy = 0.0\nsamples = 174\nvalue = [174, 0]'),
 Text(28.90507846264893, 202.67555555555555, 'X[1] <= -1.674\nentropy = 0.344\nsamples = 7348\nvalue = [6876, 472]'),
 Text(19.919450360455894, 199.9911111111111, 'X[0] <= -0.277\nentropy = 0.492\nsamples = 698\nvalue = [623, 75]'),
 Text(18.4165604754988, 197.30666666666667, 'X[0] <= -1.222\nentropy = 0.614\nsamples = 264\nvalue = [224, 40]'),
 Text(18.318010319108172, 194.6222222222222, 'entropy = 0.0\nsamples = 34\nvalue = [34, 0]'),
 Text(18.51511063188943, 194.6222222222222, 'X[0] <= -1.221\nentropy = 0.667\nsamples = 230\nvalue = [190, 40]'),
 Text(18.4165604754988, 191.93777777777777, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(18.61366078828006, 191.93777777777777, 'X[1] <= -1.765\nentropy = 0.658\nsamples = 229\nvalue = [190, 39]'),
 Text(18.51511063188943, 189.25333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(18.71221094467069, 189.25333333333333, 'X[1] <= -1.674\nentropy = 0.65\nsamples = 228\nvalue = [190, 38]'),
 Text(18.61366078828006, 186.5688888888889, 'X[1] <= -1.682\nentropy = 0.641\nsamples = 227\nvalue = [190, 37]'),
 Text(18.034678619485113, 183.88444444444445, 'X[0] <= -0.501\nentropy = 0.676\nsamples = 202\nvalue = [166, 36]'),
 Text(17.17236475106711, 181.2, 'X[0] <= -0.739\nentropy = 0.601\nsamples = 157\nvalue = [134, 23]'),
 Text(16.53178873452802, 178.51555555555555, 'X[0] <= -0.812\nentropy = 0.726\nsamples = 89\nvalue = [71, 18]'),
 Text(15.792662561598304, 175.8311111111111, 'X[1] <= -1.749\nentropy = 0.581\nsamples = 72\nvalue = [62, 10]'),
 Text(15.694112405207676, 173.14666666666668, 'entropy = 0.0\nsamples = 17\nvalue = [17, 0]'),
 Text(15.891212717988934, 173.14666666666668, 'X[0] <= -0.896\nentropy = 0.684\nsamples = 55\nvalue = [45, 10]'),
 Text(15.792662561598304, 170.46222222222224, 'X[0] <= -0.984\nentropy = 0.747\nsamples = 47\nvalue = [37, 10]'),
 Text(15.398461936035789, 167.77777777777777, 'X[1] <= -1.683\nentropy = 0.581\nsamples = 36\nvalue = [31, 5]'),
 Text(15.299911779645159, 165.09333333333333, 'X[1] <= -1.726\nentropy = 0.513\nsamples = 35\nvalue = [31, 4]'),
 Text(15.102811466863901, 162.4088888888889, 'X[1] <= -1.733\nentropy = 0.918\nsamples = 9\nvalue = [6, 3]'),
 Text(15.004261310473272, 159.72444444444443, 'entropy = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(15.20136162325453, 159.72444444444443, 'X[1] <= -1.728\nentropy = 0.811\nsamples = 4\nvalue = [1, 3]'),
 Text(15.102811466863901, 157.04, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(15.299911779645159, 157.04, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(15.497012092426417, 162.4088888888889, 'X[0] <= -1.049\nentropy = 0.235\nsamples = 26\nvalue = [25, 1]'),
 Text(15.398461936035789, 159.72444444444443, 'entropy = 0.0\nsamples = 19\nvalue = [19, 0]'),
 Text(15.595562248817046, 159.72444444444443, 'X[0] <= -1.047\nentropy = 0.592\nsamples = 7\nvalue = [6, 1]'),
 Text(15.497012092426417, 157.04, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(15.694112405207676, 157.04, 'entropy = 0.0\nsamples = 6\nvalue = [6, 0]'),
 Text(15.497012092426417, 165.09333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(16.18686318716082, 167.77777777777777, 'X[1] <= -1.727\nentropy = 0.994\nsamples = 11\nvalue = [6, 5]'),
 Text(15.989762874379561, 165.09333333333333, 'X[1] <= -1.745\nentropy = 0.863\nsamples = 7\nvalue = [5, 2]'),
 Text(15.891212717988934, 162.4088888888889, 'X[0] <= -0.964\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(15.792662561598304, 159.72444444444443, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(15.989762874379561, 159.72444444444443, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(16.08831303077019, 162.4088888888889, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(16.383963499942077, 165.09333333333333, 'X[1] <= -1.696\nentropy = 0.811\nsamples = 4\nvalue = [1, 3]'),
 Text(16.28541334355145, 162.4088888888889, 'entropy = 0.0\nsamples = 3\nvalue = [0, 3]'),
 Text(16.482513656332706, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(15.989762874379561, 170.46222222222224, 'entropy = 0.0\nsamples = 8\nvalue = [8, 0]'),
 Text(17.27091490745774, 175.8311111111111, 'X[0] <= -0.751\nentropy = 0.998\nsamples = 17\nvalue = [9, 8]'),
 Text(17.17236475106711, 173.14666666666668, 'X[0] <= -0.76\nentropy = 0.971\nsamples = 15\nvalue = [9, 6]'),
 Text(17.07381459467648, 170.46222222222224, 'X[0] <= -0.775\nentropy = 1.0\nsamples = 12\nvalue = [6, 6]'),
 Text(16.876714281895225, 167.77777777777777, 'X[0] <= -0.788\nentropy = 0.954\nsamples = 8\nvalue = [5, 3]'),
 Text(16.778164125504595, 165.09333333333333, 'X[1] <= -1.695\nentropy = 0.971\nsamples = 5\nvalue = [2, 3]'),
 Text(16.679613969113966, 162.4088888888889, 'X[1] <= -1.714\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(16.581063812723336, 159.72444444444443, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(16.778164125504595, 159.72444444444443, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(16.876714281895225, 162.4088888888889, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(16.97526443828585, 165.09333333333333, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(17.27091490745774, 167.77777777777777, 'X[1] <= -1.761\nentropy = 0.811\nsamples = 4\nvalue = [1, 3]'),
 Text(17.17236475106711, 165.09333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(17.36946506384837, 165.09333333333333, 'entropy = 0.0\nsamples = 3\nvalue = [0, 3]'),
 Text(17.27091490745774, 170.46222222222224, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(17.36946506384837, 173.14666666666668, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(17.8129407676062, 178.51555555555555, 'X[0] <= -0.665\nentropy = 0.379\nsamples = 68\nvalue = [63, 5]'),
 Text(17.71439061121557, 175.8311111111111, 'entropy = 0.0\nsamples = 22\nvalue = [22, 0]'),
 Text(17.91149092399683, 175.8311111111111, 'X[0] <= -0.664\nentropy = 0.496\nsamples = 46\nvalue = [41, 5]'),
 Text(17.8129407676062, 173.14666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(18.010041080387456, 173.14666666666668, 'X[1] <= -1.706\nentropy = 0.433\nsamples = 45\nvalue = [41, 4]'),
 Text(17.91149092399683, 170.46222222222224, 'X[1] <= -1.733\nentropy = 0.555\nsamples = 31\nvalue = [27, 4]'),
 Text(17.665115533020256, 167.77777777777777, 'X[1] <= -1.755\nentropy = 0.286\nsamples = 20\nvalue = [19, 1]'),
 Text(17.566565376629626, 165.09333333333333, 'X[0] <= -0.595\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(17.468015220238996, 162.4088888888889, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(17.665115533020256, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(17.763665689410885, 165.09333333333333, 'entropy = 0.0\nsamples = 17\nvalue = [17, 0]'),
 Text(18.1578663149734, 167.77777777777777, 'X[0] <= -0.626\nentropy = 0.845\nsamples = 11\nvalue = [8, 3]'),
 Text(17.960766002192145, 165.09333333333333, 'X[1] <= -1.71\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(17.862215845801515, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(18.05931615858277, 162.4088888888889, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(18.35496662775466, 165.09333333333333, 'X[1] <= -1.731\nentropy = 0.544\nsamples = 8\nvalue = [7, 1]'),
 Text(18.25641647136403, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(18.45351678414529, 162.4088888888889, 'entropy = 0.0\nsamples = 7\nvalue = [7, 0]'),
 Text(18.108591236778086, 170.46222222222224, 'entropy = 0.0\nsamples = 14\nvalue = [14, 0]'),
 Text(18.89699248790312, 181.2, 'X[0] <= -0.497\nentropy = 0.867\nsamples = 45\nvalue = [32, 13]'),
 Text(18.79844233151249, 178.51555555555555, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(18.99554264429375, 178.51555555555555, 'X[1] <= -1.753\nentropy = 0.82\nsamples = 43\nvalue = [32, 11]'),
 Text(18.749167253317175, 175.8311111111111, 'X[1] <= -1.758\nentropy = 1.0\nsamples = 10\nvalue = [5, 5]'),
 Text(18.650617096926545, 173.14666666666668, 'X[1] <= -1.762\nentropy = 0.863\nsamples = 7\nvalue = [5, 2]'),
 Text(18.552066940535916, 170.46222222222224, 'X[1] <= -1.763\nentropy = 1.0\nsamples = 4\nvalue = [2, 2]'),
 Text(18.45351678414529, 167.77777777777777, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(18.650617096926545, 167.77777777777777, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(18.749167253317175, 170.46222222222224, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(18.847717409707805, 173.14666666666668, 'entropy = 0.0\nsamples = 3\nvalue = [0, 3]'),
 Text(19.24191803527032, 175.8311111111111, 'X[0] <= -0.281\nentropy = 0.684\nsamples = 33\nvalue = [27, 6]'),
 Text(19.14336787887969, 173.14666666666668, 'X[0] <= -0.394\nentropy = 0.625\nsamples = 32\nvalue = [27, 5]'),
 Text(18.946267566098435, 170.46222222222224, 'X[0] <= -0.396\nentropy = 0.837\nsamples = 15\nvalue = [11, 4]'),
 Text(18.847717409707805, 167.77777777777777, 'X[0] <= -0.428\nentropy = 0.75\nsamples = 14\nvalue = [11, 3]'),
 Text(18.749167253317175, 165.09333333333333, 'X[0] <= -0.434\nentropy = 0.881\nsamples = 10\nvalue = [7, 3]'),
 Text(18.650617096926545, 162.4088888888889, 'X[0] <= -0.458\nentropy = 0.764\nsamples = 9\nvalue = [7, 2]'),
 Text(18.552066940535916, 159.72444444444443, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(18.749167253317175, 159.72444444444443, 'X[0] <= -0.449\nentropy = 0.918\nsamples = 6\nvalue = [4, 2]'),
 Text(18.650617096926545, 157.04, 'X[0] <= -0.456\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(18.552066940535916, 154.35555555555555, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(18.749167253317175, 154.35555555555555, 'X[1] <= -1.74\nentropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(18.650617096926545, 151.67111111111112, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(18.847717409707805, 151.67111111111112, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(18.847717409707805, 157.04, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(18.847717409707805, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(18.946267566098435, 165.09333333333333, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(19.044817722489064, 167.77777777777777, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(19.34046819166095, 170.46222222222224, 'X[1] <= -1.735\nentropy = 0.323\nsamples = 17\nvalue = [16, 1]'),
 Text(19.24191803527032, 167.77777777777777, 'X[1] <= -1.743\nentropy = 0.811\nsamples = 4\nvalue = [3, 1]'),
 Text(19.14336787887969, 165.09333333333333, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(19.34046819166095, 165.09333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(19.43901834805158, 167.77777777777777, 'entropy = 0.0\nsamples = 13\nvalue = [13, 0]'),
 Text(19.34046819166095, 173.14666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(19.192642957075005, 183.88444444444445, 'X[1] <= -1.676\nentropy = 0.242\nsamples = 25\nvalue = [24, 1]'),
 Text(19.094092800684376, 181.2, 'entropy = 0.0\nsamples = 19\nvalue = [19, 0]'),
 Text(19.291193113465635, 181.2, 'X[1] <= -1.675\nentropy = 0.65\nsamples = 6\nvalue = [5, 1]'),
 Text(19.192642957075005, 178.51555555555555, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(19.389743269856265, 178.51555555555555, 'entropy = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(18.810761101061317, 186.5688888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(21.42234024541299, 197.30666666666667, 'X[0] <= -0.109\nentropy = 0.404\nsamples = 434\nvalue = [399, 35]'),
 Text(21.32379008902236, 194.6222222222222, 'entropy = 0.0\nsamples = 58\nvalue = [58, 0]'),
 Text(21.520890401803616, 194.6222222222222, 'X[0] <= 1.594\nentropy = 0.447\nsamples = 376\nvalue = [341, 35]'),
 Text(21.42234024541299, 191.93777777777777, 'X[0] <= 0.809\nentropy = 0.47\nsamples = 349\nvalue = [314, 35]'),
 Text(20.473794990153184, 189.25333333333333, 'X[0] <= 0.23\nentropy = 0.375\nsamples = 221\nvalue = [205, 16]'),
 Text(20.22741959917661, 186.5688888888889, 'X[0] <= 0.209\nentropy = 0.524\nsamples = 110\nvalue = [97, 13]'),
 Text(20.030319286395354, 183.88444444444445, 'X[1] <= -1.676\nentropy = 0.478\nsamples = 107\nvalue = [96, 11]'),
 Text(19.931769130004724, 181.2, 'X[0] <= -0.103\nentropy = 0.451\nsamples = 106\nvalue = [96, 10]'),
 Text(19.833218973614095, 178.51555555555555, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(20.030319286395354, 178.51555555555555, 'X[0] <= 0.171\nentropy = 0.422\nsamples = 105\nvalue = [96, 9]'),
 Text(19.931769130004724, 175.8311111111111, 'X[0] <= 0.167\nentropy = 0.455\nsamples = 94\nvalue = [85, 9]'),
 Text(19.833218973614095, 173.14666666666668, 'X[0] <= 0.14\nentropy = 0.423\nsamples = 93\nvalue = [85, 8]'),
 Text(19.734668817223465, 170.46222222222224, 'X[0] <= 0.137\nentropy = 0.465\nsamples = 81\nvalue = [73, 8]'),
 Text(19.636118660832835, 167.77777777777777, 'X[0] <= 0.081\nentropy = 0.428\nsamples = 80\nvalue = [73, 7]'),
 Text(19.53756850444221, 165.09333333333333, 'X[0] <= 0.071\nentropy = 0.469\nsamples = 70\nvalue = [63, 7]'),
 Text(19.24191803527032, 162.4088888888889, 'X[1] <= -1.726\nentropy = 0.4\nsamples = 63\nvalue = [58, 5]'),
 Text(19.14336787887969, 159.72444444444443, 'entropy = 0.0\nsamples = 21\nvalue = [21, 0]'),
 Text(19.34046819166095, 159.72444444444443, 'X[1] <= -1.724\nentropy = 0.527\nsamples = 42\nvalue = [37, 5]'),
 Text(19.24191803527032, 157.04, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(19.43901834805158, 157.04, 'X[0] <= -0.009\nentropy = 0.461\nsamples = 41\nvalue = [37, 4]'),
 Text(19.34046819166095, 154.35555555555555, 'X[0] <= -0.012\nentropy = 0.667\nsamples = 23\nvalue = [19, 4]'),
 Text(19.24191803527032, 151.67111111111112, 'X[0] <= -0.044\nentropy = 0.575\nsamples = 22\nvalue = [19, 3]'),
 Text(19.14336787887969, 148.98666666666668, 'X[1] <= -1.704\nentropy = 0.845\nsamples = 11\nvalue = [8, 3]'),
 Text(19.044817722489064, 146.3022222222222, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(19.24191803527032, 146.3022222222222, 'X[1] <= -1.695\nentropy = 0.985\nsamples = 7\nvalue = [4, 3]'),
 Text(19.14336787887969, 143.61777777777777, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(19.34046819166095, 143.61777777777777, 'X[0] <= -0.048\nentropy = 0.722\nsamples = 5\nvalue = [4, 1]'),
 Text(19.24191803527032, 140.93333333333334, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(19.43901834805158, 140.93333333333334, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(19.34046819166095, 148.98666666666668, 'entropy = 0.0\nsamples = 11\nvalue = [11, 0]'),
 Text(19.43901834805158, 151.67111111111112, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(19.53756850444221, 154.35555555555555, 'entropy = 0.0\nsamples = 18\nvalue = [18, 0]'),
 Text(19.833218973614095, 162.4088888888889, 'X[1] <= -1.735\nentropy = 0.863\nsamples = 7\nvalue = [5, 2]'),
 Text(19.734668817223465, 159.72444444444443, 'X[0] <= 0.075\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(19.636118660832835, 157.04, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(19.833218973614095, 157.04, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(19.931769130004724, 159.72444444444443, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(19.734668817223465, 165.09333333333333, 'entropy = 0.0\nsamples = 10\nvalue = [10, 0]'),
 Text(19.833218973614095, 167.77777777777777, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(19.931769130004724, 170.46222222222224, 'entropy = 0.0\nsamples = 12\nvalue = [12, 0]'),
 Text(20.030319286395354, 173.14666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(20.128869442785984, 175.8311111111111, 'entropy = 0.0\nsamples = 11\nvalue = [11, 0]'),
 Text(20.128869442785984, 181.2, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(20.42451991195787, 183.88444444444445, 'X[1] <= -1.698\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(20.32596975556724, 181.2, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(20.5230700683485, 181.2, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(20.720170381129755, 186.5688888888889, 'X[0] <= 0.672\nentropy = 0.179\nsamples = 111\nvalue = [108, 3]'),
 Text(20.62162022473913, 183.88444444444445, 'entropy = 0.0\nsamples = 79\nvalue = [79, 0]'),
 Text(20.818720537520385, 183.88444444444445, 'X[0] <= 0.697\nentropy = 0.449\nsamples = 32\nvalue = [29, 3]'),
 Text(20.720170381129755, 181.2, 'X[1] <= -1.727\nentropy = 1.0\nsamples = 6\nvalue = [3, 3]'),
 Text(20.62162022473913, 178.51555555555555, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(20.818720537520385, 178.51555555555555, 'X[1] <= -1.689\nentropy = 0.811\nsamples = 4\nvalue = [1, 3]'),
 Text(20.720170381129755, 175.8311111111111, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(20.917270693911014, 175.8311111111111, 'X[0] <= 0.681\nentropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(20.818720537520385, 173.14666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(21.015820850301644, 173.14666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(20.917270693911014, 181.2, 'entropy = 0.0\nsamples = 26\nvalue = [26, 0]'),
 Text(22.37088550067279, 189.25333333333333, 'X[1] <= -1.688\nentropy = 0.606\nsamples = 128\nvalue = [109, 19]'),
 Text(21.85349717962199, 186.5688888888889, 'X[1] <= -1.712\nentropy = 0.507\nsamples = 98\nvalue = [87, 11]'),
 Text(21.50857163225479, 183.88444444444445, 'X[1] <= -1.765\nentropy = 0.722\nsamples = 50\nvalue = [40, 10]'),
 Text(21.41002147586416, 181.2, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(21.60712178864542, 181.2, 'X[1] <= -1.741\nentropy = 0.688\nsamples = 49\nvalue = [40, 9]'),
 Text(21.41002147586416, 178.51555555555555, 'X[1] <= -1.758\nentropy = 0.31\nsamples = 18\nvalue = [17, 1]'),
 Text(21.31147131947353, 175.8311111111111, 'X[1] <= -1.762\nentropy = 0.811\nsamples = 4\nvalue = [3, 1]'),
 Text(21.2129211630829, 173.14666666666668, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(21.41002147586416, 173.14666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(21.50857163225479, 175.8311111111111, 'entropy = 0.0\nsamples = 14\nvalue = [14, 0]'),
 Text(21.804222101426674, 178.51555555555555, 'X[1] <= -1.738\nentropy = 0.824\nsamples = 31\nvalue = [23, 8]'),
 Text(21.70567194503605, 175.8311111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(21.902772257817304, 175.8311111111111, 'X[1] <= -1.713\nentropy = 0.784\nsamples = 30\nvalue = [23, 7]'),
 Text(21.804222101426674, 173.14666666666668, 'X[1] <= -1.714\nentropy = 0.736\nsamples = 29\nvalue = [23, 6]'),
 Text(21.70567194503605, 170.46222222222224, 'X[1] <= -1.715\nentropy = 0.811\nsamples = 24\nvalue = [18, 6]'),
 Text(21.60712178864542, 167.77777777777777, 'X[1] <= -1.73\nentropy = 0.755\nsamples = 23\nvalue = [18, 5]'),
 Text(21.41002147586416, 165.09333333333333, 'X[0] <= 1.005\nentropy = 0.954\nsamples = 8\nvalue = [5, 3]'),
 Text(21.31147131947353, 162.4088888888889, 'entropy = 0.0\nsamples = 3\nvalue = [0, 3]'),
 Text(21.50857163225479, 162.4088888888889, 'entropy = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(21.804222101426674, 165.09333333333333, 'X[0] <= 1.419\nentropy = 0.567\nsamples = 15\nvalue = [13, 2]'),
 Text(21.70567194503605, 162.4088888888889, 'X[1] <= -1.717\nentropy = 0.371\nsamples = 14\nvalue = [13, 1]'),
 Text(21.60712178864542, 159.72444444444443, 'entropy = 0.0\nsamples = 12\nvalue = [12, 0]'),
 Text(21.804222101426674, 159.72444444444443, 'X[0] <= 1.047\nentropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(21.70567194503605, 157.04, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(21.902772257817304, 157.04, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(21.902772257817304, 162.4088888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(21.804222101426674, 167.77777777777777, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(21.902772257817304, 170.46222222222224, 'entropy = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(22.001322414207934, 173.14666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(22.198422726989193, 183.88444444444445, 'X[0] <= 0.853\nentropy = 0.146\nsamples = 48\nvalue = [47, 1]'),
 Text(22.099872570598563, 181.2, 'X[0] <= 0.85\nentropy = 0.811\nsamples = 4\nvalue = [3, 1]'),
 Text(22.001322414207934, 178.51555555555555, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(22.198422726989193, 178.51555555555555, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(22.29697288337982, 181.2, 'entropy = 0.0\nsamples = 44\nvalue = [44, 0]'),
 Text(22.888273821723594, 186.5688888888889, 'X[1] <= -1.68\nentropy = 0.837\nsamples = 30\nvalue = [22, 8]'),
 Text(22.59262335255171, 183.88444444444445, 'X[0] <= 0.812\nentropy = 0.971\nsamples = 15\nvalue = [9, 6]'),
 Text(22.49407319616108, 181.2, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(22.691173508942338, 181.2, 'X[1] <= -1.686\nentropy = 0.94\nsamples = 14\nvalue = [9, 5]'),
 Text(22.59262335255171, 178.51555555555555, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(22.789723665332968, 178.51555555555555, 'X[0] <= 0.977\nentropy = 1.0\nsamples = 10\nvalue = [5, 5]'),
 Text(22.691173508942338, 175.8311111111111, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(22.888273821723594, 175.8311111111111, 'X[0] <= 1.081\nentropy = 0.954\nsamples = 8\nvalue = [3, 5]'),
 Text(22.789723665332968, 173.14666666666668, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(22.986823978114224, 173.14666666666668, 'X[1] <= -1.685\nentropy = 1.0\nsamples = 6\nvalue = [3, 3]'),
 Text(22.888273821723594, 170.46222222222224, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(23.085374134504853, 170.46222222222224, 'X[1] <= -1.682\nentropy = 0.971\nsamples = 5\nvalue = [3, 2]'),
 Text(22.986823978114224, 167.77777777777777, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(23.183924290895483, 167.77777777777777, 'X[0] <= 1.212\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(23.085374134504853, 165.09333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(23.282474447286113, 165.09333333333333, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(23.183924290895483, 183.88444444444445, 'X[0] <= 1.581\nentropy = 0.567\nsamples = 15\nvalue = [13, 2]'),
 Text(23.085374134504853, 181.2, 'X[1] <= -1.676\nentropy = 0.371\nsamples = 14\nvalue = [13, 1]'),
 Text(22.986823978114224, 178.51555555555555, 'entropy = 0.0\nsamples = 10\nvalue = [10, 0]'),
 Text(23.183924290895483, 178.51555555555555, 'X[1] <= -1.676\nentropy = 0.811\nsamples = 4\nvalue = [3, 1]'),
 Text(23.085374134504853, 175.8311111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(23.282474447286113, 175.8311111111111, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(23.282474447286113, 181.2, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(21.619440558194245, 191.93777777777777, 'entropy = 0.0\nsamples = 27\nvalue = [27, 0]'),
 Text(37.89070656484196, 199.9911111111111, 'X[0] <= 0.049\nentropy = 0.326\nsamples = 6650\nvalue = [6253, 397]'),
 Text(27.669496252862707, 197.30666666666667, 'X[1] <= -1.275\nentropy = 0.273\nsamples = 2834\nvalue = [2701, 133]'),
 Text(25.11797111006158, 194.6222222222222, 'X[0] <= -1.299\nentropy = 0.231\nsamples = 1888\nvalue = [1817, 71]'),
 Text(24.317251089387717, 191.93777777777777, 'X[0] <= -1.316\nentropy = 0.42\nsamples = 129\nvalue = [118, 11]'),
 Text(23.676675072848628, 189.25333333333333, 'X[0] <= -1.406\nentropy = 0.301\nsamples = 112\nvalue = [106, 6]'),
 Text(23.578124916458, 186.5688888888889, 'entropy = 0.0\nsamples = 20\nvalue = [20, 0]'),
 Text(23.775225229239258, 186.5688888888889, 'X[0] <= -1.405\nentropy = 0.348\nsamples = 92\nvalue = [86, 6]'),
 Text(23.676675072848628, 183.88444444444445, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(23.873775385629887, 183.88444444444445, 'X[0] <= -1.375\nentropy = 0.307\nsamples = 91\nvalue = [86, 5]'),
 Text(23.676675072848628, 181.2, 'X[0] <= -1.377\nentropy = 0.529\nsamples = 25\nvalue = [22, 3]'),
 Text(23.578124916458, 178.51555555555555, 'X[1] <= -1.386\nentropy = 0.414\nsamples = 24\nvalue = [22, 2]'),
 Text(23.47957476006737, 175.8311111111111, 'entropy = 0.0\nsamples = 14\nvalue = [14, 0]'),
 Text(23.676675072848628, 175.8311111111111, 'X[1] <= -1.368\nentropy = 0.722\nsamples = 10\nvalue = [8, 2]'),
 Text(23.578124916458, 173.14666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(23.775225229239258, 173.14666666666668, 'X[1] <= -1.297\nentropy = 0.503\nsamples = 9\nvalue = [8, 1]'),
 Text(23.676675072848628, 170.46222222222224, 'entropy = 0.0\nsamples = 6\nvalue = [6, 0]'),
 Text(23.873775385629887, 170.46222222222224, 'X[1] <= -1.294\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(23.775225229239258, 167.77777777777777, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(23.972325542020513, 167.77777777777777, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(23.775225229239258, 178.51555555555555, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(24.070875698411143, 181.2, 'X[1] <= -1.667\nentropy = 0.196\nsamples = 66\nvalue = [64, 2]'),
 Text(23.972325542020513, 178.51555555555555, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(24.169425854801773, 178.51555555555555, 'X[0] <= -1.333\nentropy = 0.115\nsamples = 65\nvalue = [64, 1]'),
 Text(24.070875698411143, 175.8311111111111, 'entropy = 0.0\nsamples = 47\nvalue = [47, 0]'),
 Text(24.267976011192403, 175.8311111111111, 'X[0] <= -1.333\nentropy = 0.31\nsamples = 18\nvalue = [17, 1]'),
 Text(24.169425854801773, 173.14666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(24.366526167583032, 173.14666666666668, 'entropy = 0.0\nsamples = 17\nvalue = [17, 0]'),
 Text(24.957827105926807, 189.25333333333333, 'X[1] <= -1.337\nentropy = 0.874\nsamples = 17\nvalue = [12, 5]'),
 Text(24.859276949536177, 186.5688888888889, 'X[1] <= -1.383\nentropy = 0.994\nsamples = 11\nvalue = [6, 5]'),
 Text(24.760726793145547, 183.88444444444445, 'X[1] <= -1.552\nentropy = 0.918\nsamples = 9\nvalue = [6, 3]'),
 Text(24.662176636754918, 181.2, 'X[0] <= -1.31\nentropy = 0.971\nsamples = 5\nvalue = [2, 3]'),
 Text(24.563626480364288, 178.51555555555555, 'X[1] <= -1.562\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(24.46507632397366, 175.8311111111111, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(24.662176636754918, 175.8311111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(24.760726793145547, 178.51555555555555, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(24.859276949536177, 181.2, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(24.957827105926807, 183.88444444444445, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(25.056377262317433, 186.5688888888889, 'entropy = 0.0\nsamples = 6\nvalue = [6, 0]'),
 Text(25.91869113073544, 191.93777777777777, 'X[0] <= 0.004\nentropy = 0.215\nsamples = 1759\nvalue = [1699, 60]'),
 Text(25.82014097434481, 189.25333333333333, 'X[0] <= 0.004\nentropy = 0.222\nsamples = 1679\nvalue = [1619, 60]'),
 Text(25.72159081795418, 186.5688888888889, 'X[1] <= -1.364\nentropy = 0.22\nsamples = 1678\nvalue = [1619, 59]'),
 Text(25.154927418708063, 183.88444444444445, 'X[1] <= -1.364\nentropy = 0.237\nsamples = 1337\nvalue = [1285, 52]'),
 Text(25.056377262317433, 181.2, 'X[0] <= -1.187\nentropy = 0.234\nsamples = 1335\nvalue = [1284, 51]'),
 Text(24.957827105926807, 178.51555555555555, 'entropy = 0.0\nsamples = 84\nvalue = [84, 0]'),
 Text(25.154927418708063, 178.51555555555555, 'X[0] <= -1.186\nentropy = 0.246\nsamples = 1251\nvalue = [1200, 51]'),
 Text(25.056377262317433, 175.8311111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(25.253477575098692, 175.8311111111111, 'X[1] <= -1.377\nentropy = 0.242\nsamples = 1250\nvalue = [1200, 50]'),
 Text(25.154927418708063, 173.14666666666668, 'X[1] <= -1.377\nentropy = 0.25\nsamples = 1199\nvalue = [1149, 50]'),
 Text(25.056377262317433, 170.46222222222224, 'X[1] <= -1.4\nentropy = 0.246\nsamples = 1198\nvalue = [1149, 49]'),
 Text(24.46507632397366, 167.77777777777777, 'X[1] <= -1.661\nentropy = 0.229\nsamples = 1102\nvalue = [1061, 41]'),
 Text(24.366526167583032, 165.09333333333333, 'entropy = 0.0\nsamples = 38\nvalue = [38, 0]'),
 Text(24.563626480364288, 165.09333333333333, 'X[1] <= -1.659\nentropy = 0.236\nsamples = 1064\nvalue = [1023, 41]'),
 Text(24.218700932997088, 162.4088888888889, 'X[1] <= -1.66\nentropy = 0.954\nsamples = 8\nvalue = [5, 3]'),
 Text(24.120150776606458, 159.72444444444443, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(24.317251089387717, 159.72444444444443, 'X[1] <= -1.659\nentropy = 0.863\nsamples = 7\nvalue = [5, 2]'),
 Text(24.218700932997088, 157.04, 'X[0] <= -0.46\nentropy = 0.65\nsamples = 6\nvalue = [5, 1]'),
 Text(24.120150776606458, 154.35555555555555, 'X[1] <= -1.659\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(24.02160062021583, 151.67111111111112, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(24.218700932997088, 151.67111111111112, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(24.317251089387717, 154.35555555555555, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(24.415801245778347, 157.04, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(24.908552027731492, 162.4088888888889, 'X[0] <= -1.181\nentropy = 0.224\nsamples = 1056\nvalue = [1018, 38]'),
 Text(24.711451714950233, 159.72444444444443, 'X[0] <= -1.183\nentropy = 0.811\nsamples = 4\nvalue = [3, 1]'),
 Text(24.612901558559603, 157.04, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(24.810001871340862, 157.04, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(25.105652340512748, 159.72444444444443, 'X[0] <= -1.09\nentropy = 0.22\nsamples = 1052\nvalue = [1015, 37]'),
 Text(25.007102184122118, 157.04, 'entropy = 0.0\nsamples = 63\nvalue = [63, 0]'),
 Text(25.204202496903378, 157.04, 'X[0] <= -1.089\nentropy = 0.23\nsamples = 989\nvalue = [952, 37]'),
 Text(25.105652340512748, 154.35555555555555, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(25.302752653294007, 154.35555555555555, 'X[0] <= -0.962\nentropy = 0.226\nsamples = 988\nvalue = [952, 36]'),
 Text(25.090638840125113, 151.67111111111112, 'X[0] <= -1.061\nentropy = 0.081\nsamples = 100\nvalue = [99, 1]'),
 Text(24.992088683734483, 148.98666666666668, 'X[0] <= -1.065\nentropy = 0.222\nsamples = 28\nvalue = [27, 1]'),
 Text(24.893538527343857, 146.3022222222222, 'entropy = 0.0\nsamples = 27\nvalue = [27, 0]'),
 Text(25.090638840125113, 146.3022222222222, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(25.189188996515743, 148.98666666666668, 'entropy = 0.0\nsamples = 72\nvalue = [72, 0]'),
 Text(25.514866466462898, 151.67111111111112, 'X[0] <= -0.957\nentropy = 0.24\nsamples = 888\nvalue = [853, 35]'),
 Text(25.416316310072272, 148.98666666666668, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(25.613416622853528, 148.98666666666668, 'X[0] <= -0.921\nentropy = 0.235\nsamples = 887\nvalue = [853, 34]'),
 Text(25.287739152906372, 146.3022222222222, 'X[0] <= -0.926\nentropy = 0.516\nsamples = 26\nvalue = [23, 3]'),
 Text(25.189188996515743, 143.61777777777777, 'entropy = 0.0\nsamples = 22\nvalue = [22, 0]'),
 Text(25.386289309297002, 143.61777777777777, 'X[1] <= -1.482\nentropy = 0.811\nsamples = 4\nvalue = [1, 3]'),
 Text(25.287739152906372, 140.93333333333334, 'X[1] <= -1.583\nentropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(25.189188996515743, 138.24888888888887, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(25.386289309297002, 138.24888888888887, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(25.48483946568763, 140.93333333333334, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(25.939094092800687, 146.3022222222222, 'X[0] <= -0.858\nentropy = 0.224\nsamples = 861\nvalue = [830, 31]'),
 Text(25.840543936410057, 143.61777777777777, 'entropy = 0.0\nsamples = 51\nvalue = [51, 0]'),
 Text(26.037644249191313, 143.61777777777777, 'X[0] <= -0.85\nentropy = 0.234\nsamples = 810\nvalue = [779, 31]'),
 Text(25.681939778468887, 140.93333333333334, 'X[1] <= -1.588\nentropy = 0.985\nsamples = 7\nvalue = [4, 3]'),
 Text(25.583389622078258, 138.24888888888887, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(25.780489934859517, 138.24888888888887, 'X[1] <= -1.543\nentropy = 0.971\nsamples = 5\nvalue = [2, 3]'),
 Text(25.681939778468887, 135.56444444444446, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(25.879040091250147, 135.56444444444446, 'X[0] <= -0.853\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(25.780489934859517, 132.88, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(25.977590247640777, 132.88, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(26.393348719913742, 140.93333333333334, 'X[0] <= -0.767\nentropy = 0.218\nsamples = 803\nvalue = [775, 28]'),
 Text(26.294798563523113, 138.24888888888887, 'entropy = 0.0\nsamples = 56\nvalue = [56, 0]'),
 Text(26.491898876304372, 138.24888888888887, 'X[0] <= -0.766\nentropy = 0.231\nsamples = 747\nvalue = [719, 28]'),
 Text(26.393348719913742, 135.56444444444446, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(26.590449032695, 135.56444444444446, 'X[0] <= -0.647\nentropy = 0.225\nsamples = 745\nvalue = [718, 27]'),
 Text(26.174690560422032, 132.88, 'X[0] <= -0.727\nentropy = 0.081\nsamples = 100\nvalue = [99, 1]'),
 Text(26.076140404031403, 130.19555555555556, 'X[0] <= -0.729\nentropy = 0.267\nsamples = 22\nvalue = [21, 1]'),
 Text(25.977590247640777, 127.5111111111111, 'entropy = 0.0\nsamples = 21\nvalue = [21, 0]'),
 Text(26.174690560422032, 127.5111111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(26.273240716812662, 130.19555555555556, 'entropy = 0.0\nsamples = 78\nvalue = [78, 0]'),
 Text(27.006207504967964, 132.88, 'X[0] <= -0.646\nentropy = 0.244\nsamples = 645\nvalue = [619, 26]'),
 Text(26.907657348577338, 130.19555555555556, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(27.104757661358594, 130.19555555555556, 'X[0] <= -0.443\nentropy = 0.237\nsamples = 644\nvalue = [619, 25]'),
 Text(26.37179087320329, 127.5111111111111, 'X[0] <= -0.455\nentropy = 0.331\nsamples = 164\nvalue = [154, 10]'),
 Text(25.903677630347804, 124.82666666666667, 'X[1] <= -1.444\nentropy = 0.262\nsamples = 158\nvalue = [151, 7]'),
 Text(25.5587520829806, 122.14222222222222, 'X[0] <= -0.564\nentropy = 0.196\nsamples = 132\nvalue = [128, 4]'),
 Text(25.460201926589974, 119.45777777777778, 'entropy = 0.0\nsamples = 49\nvalue = [49, 0]'),
 Text(25.65730223937123, 119.45777777777778, 'X[0] <= -0.563\nentropy = 0.279\nsamples = 83\nvalue = [79, 4]'),
 Text(25.5587520829806, 116.77333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(25.75585239576186, 116.77333333333333, 'X[0] <= -0.516\nentropy = 0.226\nsamples = 82\nvalue = [79, 3]'),
 Text(25.65730223937123, 114.08888888888889, 'entropy = 0.0\nsamples = 38\nvalue = [38, 0]'),
 Text(25.85440255215249, 114.08888888888889, 'X[0] <= -0.505\nentropy = 0.359\nsamples = 44\nvalue = [41, 3]'),
 Text(25.65730223937123, 111.40444444444444, 'X[1] <= -1.57\nentropy = 0.971\nsamples = 5\nvalue = [3, 2]'),
 Text(25.5587520829806, 108.72, 'X[0] <= -0.508\nentropy = 0.811\nsamples = 4\nvalue = [3, 1]'),
 Text(25.460201926589974, 106.03555555555556, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(25.65730223937123, 106.03555555555556, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(25.75585239576186, 108.72, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(26.051502864933745, 111.40444444444444, 'X[1] <= -1.471\nentropy = 0.172\nsamples = 39\nvalue = [38, 1]'),
 Text(25.95295270854312, 108.72, 'entropy = 0.0\nsamples = 32\nvalue = [32, 0]'),
 Text(26.150053021324375, 108.72, 'X[0] <= -0.467\nentropy = 0.592\nsamples = 7\nvalue = [6, 1]'),
 Text(26.051502864933745, 106.03555555555556, 'entropy = 0.0\nsamples = 6\nvalue = [6, 0]'),
 Text(26.248603177715005, 106.03555555555556, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(26.248603177715005, 122.14222222222222, 'X[1] <= -1.442\nentropy = 0.516\nsamples = 26\nvalue = [23, 3]'),
 Text(26.051502864933745, 119.45777777777778, 'X[0] <= -0.606\nentropy = 0.918\nsamples = 3\nvalue = [1, 2]'),
 Text(25.95295270854312, 116.77333333333333, 'entropy = 1.0\nsamples = 2\nvalue = [1, 1]'),
 Text(26.150053021324375, 116.77333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(26.445703490496264, 119.45777777777778, 'X[0] <= -0.493\nentropy = 0.258\nsamples = 23\nvalue = [22, 1]'),
 Text(26.347153334105634, 116.77333333333333, 'entropy = 0.0\nsamples = 18\nvalue = [18, 0]'),
 Text(26.544253646886894, 116.77333333333333, 'X[1] <= -1.413\nentropy = 0.722\nsamples = 5\nvalue = [4, 1]'),
 Text(26.445703490496264, 114.08888888888889, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(26.64280380327752, 114.08888888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(26.83990411605878, 124.82666666666667, 'X[1] <= -1.584\nentropy = 1.0\nsamples = 6\nvalue = [3, 3]'),
 Text(26.74135395966815, 122.14222222222222, 'entropy = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(26.93845427244941, 122.14222222222222, 'X[0] <= -0.451\nentropy = 0.971\nsamples = 5\nvalue = [2, 3]'),
 Text(26.83990411605878, 119.45777777777778, 'X[0] <= -0.454\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(26.74135395966815, 116.77333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(26.93845427244941, 116.77333333333333, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(27.03700442884004, 119.45777777777778, 'entropy = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(27.8377244495139, 127.5111111111111, 'X[0] <= -0.239\nentropy = 0.201\nsamples = 480\nvalue = [465, 15]'),
 Text(27.529755210793184, 124.82666666666667, 'X[1] <= -1.422\nentropy = 0.073\nsamples = 225\nvalue = [223, 2]'),
 Text(27.332654898011924, 122.14222222222222, 'X[1] <= -1.612\nentropy = 0.043\nsamples = 212\nvalue = [211, 1]'),
 Text(27.234104741621294, 119.45777777777778, 'X[1] <= -1.615\nentropy = 0.258\nsamples = 23\nvalue = [22, 1]'),
 Text(27.135554585230665, 116.77333333333333, 'entropy = 0.0\nsamples = 22\nvalue = [22, 0]'),
 Text(27.332654898011924, 116.77333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(27.431205054402554, 119.45777777777778, 'entropy = 0.0\nsamples = 189\nvalue = [189, 0]'),
 Text(27.72685552357444, 122.14222222222222, 'X[1] <= -1.421\nentropy = 0.391\nsamples = 13\nvalue = [12, 1]'),
 Text(27.628305367183813, 119.45777777777778, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(27.82540567996507, 119.45777777777778, 'entropy = 0.0\nsamples = 12\nvalue = [12, 0]'),
 Text(28.145693688234616, 124.82666666666667, 'X[0] <= -0.238\nentropy = 0.291\nsamples = 255\nvalue = [242, 13]'),
 Text(28.047143531843986, 122.14222222222222, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(28.24424384462524, 122.14222222222222, 'X[1] <= -1.489\nentropy = 0.275\nsamples = 254\nvalue = [242, 12]'),
 Text(28.02250599274633, 119.45777777777778, 'X[1] <= -1.49\nentropy = 0.319\nsamples = 190\nvalue = [179, 11]'),
 Text(27.9239558363557, 116.77333333333333, 'X[1] <= -1.645\nentropy = 0.299\nsamples = 189\nvalue = [179, 10]'),
 Text(27.5790302889885, 114.08888888888889, 'X[1] <= -1.646\nentropy = 0.592\nsamples = 14\nvalue = [12, 2]'),
 Text(27.48048013259787, 111.40444444444444, 'X[0] <= -0.157\nentropy = 0.391\nsamples = 13\nvalue = [12, 1]'),
 Text(27.38192997620724, 108.72, 'entropy = 0.0\nsamples = 8\nvalue = [8, 0]'),
 Text(27.5790302889885, 108.72, 'X[0] <= -0.121\nentropy = 0.722\nsamples = 5\nvalue = [4, 1]'),
 Text(27.48048013259787, 106.03555555555556, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(27.677580445379125, 106.03555555555556, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(27.677580445379125, 111.40444444444444, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(28.2688813837229, 114.08888888888889, 'X[1] <= -1.573\nentropy = 0.268\nsamples = 175\nvalue = [167, 8]'),
 Text(28.071781070941643, 111.40444444444444, 'X[0] <= -0.132\nentropy = 0.155\nsamples = 89\nvalue = [87, 2]'),
 Text(27.973230914551014, 108.72, 'X[0] <= -0.136\nentropy = 0.31\nsamples = 36\nvalue = [34, 2]'),
 Text(27.874680758160384, 106.03555555555556, 'X[1] <= -1.629\nentropy = 0.187\nsamples = 35\nvalue = [34, 1]'),
 Text(27.776130601769754, 103.35111111111111, 'X[1] <= -1.631\nentropy = 0.544\nsamples = 8\nvalue = [7, 1]'),
 Text(27.677580445379125, 100.66666666666667, 'entropy = 0.0\nsamples = 7\nvalue = [7, 0]'),
 Text(27.874680758160384, 100.66666666666667, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(27.973230914551014, 103.35111111111111, 'entropy = 0.0\nsamples = 27\nvalue = [27, 0]'),
 Text(28.071781070941643, 106.03555555555556, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(28.170331227332273, 108.72, 'entropy = 0.0\nsamples = 53\nvalue = [53, 0]'),
 Text(28.46598169650416, 111.40444444444444, 'X[1] <= -1.572\nentropy = 0.365\nsamples = 86\nvalue = [80, 6]'),
 Text(28.36743154011353, 108.72, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(28.56453185289479, 108.72, 'X[0] <= -0.094\nentropy = 0.323\nsamples = 85\nvalue = [80, 5]'),
 Text(28.36743154011353, 106.03555555555556, 'X[0] <= -0.235\nentropy = 0.141\nsamples = 50\nvalue = [49, 1]'),
 Text(28.2688813837229, 103.35111111111111, 'X[1] <= -1.519\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(28.170331227332273, 100.66666666666667, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(28.36743154011353, 100.66666666666667, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(28.46598169650416, 103.35111111111111, 'entropy = 0.0\nsamples = 47\nvalue = [47, 0]'),
 Text(28.761632165676044, 106.03555555555556, 'X[0] <= -0.092\nentropy = 0.513\nsamples = 35\nvalue = [31, 4]'),
 Text(28.663082009285418, 103.35111111111111, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(28.860182322066674, 103.35111111111111, 'X[0] <= -0.069\nentropy = 0.431\nsamples = 34\nvalue = [31, 3]'),
 Text(28.761632165676044, 100.66666666666667, 'entropy = 0.0\nsamples = 11\nvalue = [11, 0]'),
 Text(28.958732478457303, 100.66666666666667, 'X[0] <= -0.067\nentropy = 0.559\nsamples = 23\nvalue = [20, 3]'),
 Text(28.860182322066674, 97.98222222222222, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(29.057282634847933, 97.98222222222222, 'X[0] <= -0.012\nentropy = 0.439\nsamples = 22\nvalue = [20, 2]'),
 Text(28.860182322066674, 95.29777777777778, 'X[0] <= -0.048\nentropy = 0.297\nsamples = 19\nvalue = [18, 1]'),
 Text(28.761632165676044, 92.61333333333333, 'X[1] <= -1.507\nentropy = 0.722\nsamples = 5\nvalue = [4, 1]'),
 Text(28.663082009285418, 89.92888888888889, 'entropy = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(28.860182322066674, 89.92888888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(28.958732478457303, 92.61333333333333, 'entropy = 0.0\nsamples = 14\nvalue = [14, 0]'),
 Text(29.254382947629193, 95.29777777777778, 'X[0] <= -0.009\nentropy = 0.918\nsamples = 3\nvalue = [2, 1]'),
 Text(29.155832791238563, 92.61333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(29.35293310401982, 92.61333333333333, 'entropy = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(28.121056149136958, 116.77333333333333, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(28.46598169650416, 119.45777777777778, 'X[1] <= -1.44\nentropy = 0.116\nsamples = 64\nvalue = [63, 1]'),
 Text(28.36743154011353, 116.77333333333333, 'entropy = 0.0\nsamples = 44\nvalue = [44, 0]'),
 Text(28.56453185289479, 116.77333333333333, 'X[1] <= -1.435\nentropy = 0.286\nsamples = 20\nvalue = [19, 1]'),
 Text(28.46598169650416, 114.08888888888889, 'entropy = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(28.663082009285418, 114.08888888888889, 'entropy = 0.0\nsamples = 19\nvalue = [19, 0]'),
 Text(25.647678200661208, 167.77777777777777, 'X[1] <= -1.397\nentropy = 0.414\nsamples = 96\nvalue = [88, 8]'),
 Text(25.302752653294007, 165.09333333333333, 'X[0] <= -0.703\nentropy = 1.0\nsamples = 10\nvalue = [5, 5]'),
 Text(25.204202496903378, 162.4088888888889, 'entropy = 0.0\nsamples = 3\nvalue = [0, 3]'),
 Text(25.401302809684637, 162.4088888888889, 'X[0] <= -0.357\nentropy = 0.863\nsamples = 7\nvalue = [5, 2]'),
 Text(25.302752653294007, 159.72444444444443, 'entropy = 0.0\nsamples = 3\nvalue = [3, 0]'),
 ...]

mae_dt = metrics.mean_absolute_error(y_test, y_pred)
mae_dt

0.17570456754130223

mse_dt = metrics.mean_squared_error(y_test, y_pred)
mse_dt

0.17570456754130223

Naive Bayes

#from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()
gnb.fit(x_train, y_train)

GaussianNB()

y_pred = gnb.predict(x_test)

print("Gaussian Naive Bayes model accuracy(in %):", metrics.accuracy_score(y_test, y_pred)*100)

Gaussian Naive Bayes model accuracy(in %): 20.02816080792387

cm_nb = confusion_matrix(y_test, y_pred)
cm_nb

array([[ 1468, 16456],
       [   15,  2657]], dtype=int64)

XGBoost

# fit model no training data
model = XGBClassifier()
model.fit(x_train, y_train)

C:\Users\SHUBHAM KUMAR\anaconda3\lib\site-packages\xgboost\sklearn.py:1224: UserWarning: The use of label encoder in XGBClassifier is deprecated and will be removed in a future release. To remove this warning, do the following: 1) Pass option use_label_encoder=False when constructing XGBClassifier object; and 2) Encode your labels (y) as integers starting with 0, i.e. 0, 1, 2, ..., [num_class - 1].
  warnings.warn(label_encoder_deprecation_msg, UserWarning)

[01:26:18] WARNING: C:/Users/Administrator/workspace/xgboost-win64_release_1.5.1/src/learner.cc:1115: Starting in XGBoost 1.3.0, the default evaluation metric used with the objective 'binary:logistic' was changed from 'error' to 'logloss'. Explicitly set eval_metric if you'd like to restore the old behavior.

XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=4,
              num_parallel_tree=1, predictor='auto', random_state=0,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', validate_parameters=1, verbosity=None)

print(model)

XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,
              gamma=0, gpu_id=-1, importance_type=None,
              interaction_constraints='', learning_rate=0.300000012,
              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,
              monotone_constraints='()', n_estimators=100, n_jobs=4,
              num_parallel_tree=1, predictor='auto', random_state=0,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,
              tree_method='exact', validate_parameters=1, verbosity=None)

# make predictions for test data
y_pred = model.predict(x_test)
predictions = [round(value) for value in y_pred]

# evaluate predictions
accuracy = accuracy_score(y_test, predictions)
print("Accuracy: %.2f%%" % (accuracy * 100.0))

Accuracy: 89.26%

cm_xgb = confusion_matrix(y_test, y_pred)
cm_xgb

array([[17818,   106],
       [ 2105,   567]], dtype=int64)

GradientBoostingClassifier

from sklearn.datasets import make_hastie_10_2
from sklearn.ensemble import GradientBoostingClassifier

x, y = make_hastie_10_2(random_state=0)

clf = GradientBoostingClassifier(n_estimators=100, learning_rate=1.0,max_depth=1, random_state=0).fit(x_train, y_train)

y_pred = classifier.predict(x_test)
print(y_pred)

[0 0 0 ... 0 0 0]

clf.score(x_test, y_test)

0.8694406680908915

cm_gbc = confusion_matrix(y_test, y_pred)
cm_gbc

array([[17908,    16],
       [ 2657,    15]], dtype=int64)

dfx = pd.DataFrame(columns=['a', 'b', 'c'])

dfx

	a	b	c
0	-3.090660	0.733887	-0.955214
1	0.584203	-0.424487	0.577758
2	-1.207929	-0.840401	1.209606
3	1.799498	-0.832761	-0.121090
4	-0.350329	-0.666571	-1.686874
...	...	...	...
195	-0.786255	0.138206	-0.465385
196	0.856177	-1.434567	0.640946
197	0.058408	0.075175	0.592933
198	-0.957589	0.169009	1.272661
199	-0.402105	1.202782	-0.412881

200 rows × 3 columns